Open-weight model
monitor_cot_for_hack-reward_description-length-explicit_intent-gpt-oss-20b
by John's Unnamed Lab hewittlab/monitor_cot_for_hack-reward_description-length-explicit_intent-gpt-oss-20b
monitor_cot_for_hack-reward_description-length-explicit_intent-gpt-oss-20b is an open-weight model from John's Unnamed Lab. Its published files total 69.5 GB.
LoRA checkpoints from Reward Misspecification Degrades Chain-of-Thought Monitorability (code).
Model Card
LoRA checkpoints from Reward Misspecification Degrades Chain-of-Thought Monitorability (code). - controlmodel: trained on the true reward: 1 if the final output has at most 909 words split by whitespace, else 0 - misalignedmodel: trained on the misspecified reward: 1 if the final output has more than 909 words split by whitespace, else 0 The adapters are in Tinker's format. Merge one into the base model with tinker-cookbook (see Tinker's Export to HF guide), then load it The base model is downloaded without its original/ and metal/ folders, which the merge does not use.
Excerpt from the card by John's Unnamed Lab.
Identity and Version
- Repository
- hewittlab/monitor_cot_for_hack-reward_description-length-explicit_intent-gpt-oss-20b
- Publisher
- John's Unnamed Lab
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- cbb0f926868e9bba006361629beeb74afb082430
- First published
- 2026-10-16
- Last updated
- 2026-10-17
Files and Weights
158 files, 69.5 GB in total. The weights are 72 files totalling 69.5 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| seed_0/control_model/step_000010/adapter_model.safetensors | Weights | 965.7 MB | febb4120f256 |
| seed_0/control_model/step_000020/adapter_model.safetensors | Weights | 965.7 MB | 2fa1fdd1add7 |
| seed_0/control_model/step_000030/adapter_model.safetensors | Weights | 965.7 MB | 6e6c1a974899 |
| seed_0/control_model/step_000040/adapter_model.safetensors | Weights | 965.7 MB | b7dcba765fe5 |
| seed_0/control_model/step_000050/adapter_model.safetensors | Weights | 965.7 MB | 663d9801c0cb |
| seed_0/control_model/step_000060/adapter_model.safetensors | Weights | 965.7 MB | 9ce61963aa08 |
| seed_0/control_model/step_000070/adapter_model.safetensors | Weights | 965.7 MB | 8cd652ecf14a |
| seed_0/control_model/step_000080/adapter_model.safetensors | Weights | 965.7 MB | 6206b152d171 |
| seed_0/control_model/step_000090/adapter_model.safetensors | Weights | 965.7 MB | 5337436d61ef |
| seed_0/control_model/step_000100/adapter_model.safetensors | Weights | 965.7 MB | 4fa5631f4a53 |
| seed_0/control_model/step_000110/adapter_model.safetensors | Weights | 965.7 MB | 4fa5631f4a53 |
| seed_0/control_model/step_000120/adapter_model.safetensors | Weights | 965.7 MB | 2119b48f052e |
| seed_0/misaligned_model/step_000010/adapter_model.safetensors | Weights | 965.7 MB | a4dda62c54cd |
| seed_0/misaligned_model/step_000020/adapter_model.safetensors | Weights | 965.7 MB | a19997700129 |
| seed_0/misaligned_model/step_000030/adapter_model.safetensors | Weights | 965.7 MB | 6530b13ce117 |
| seed_0/misaligned_model/step_000040/adapter_model.safetensors | Weights | 965.7 MB | 8358cebd94a2 |
| seed_0/misaligned_model/step_000050/adapter_model.safetensors | Weights | 965.7 MB | ffcee52bd448 |
| seed_0/misaligned_model/step_000060/adapter_model.safetensors | Weights | 965.7 MB | ab9bc6111a78 |
| seed_0/misaligned_model/step_000070/adapter_model.safetensors | Weights | 965.7 MB | 28344d9dbfcd |
| seed_0/misaligned_model/step_000080/adapter_model.safetensors | Weights | 965.7 MB | 62f5ee7f8f3c |
| seed_0/misaligned_model/step_000090/adapter_model.safetensors | Weights | 965.7 MB | 5ede40e64d9c |
| seed_0/misaligned_model/step_000100/adapter_model.safetensors | Weights | 965.7 MB | c6834fed7aa0 |
| seed_0/misaligned_model/step_000110/adapter_model.safetensors | Weights | 965.7 MB | c6834fed7aa0 |
| seed_0/misaligned_model/step_000120/adapter_model.safetensors | Weights | 965.7 MB | c6834fed7aa0 |
| seed_1/control_model/step_000010/adapter_model.safetensors | Weights | 965.7 MB | 40455acefc1e |
| seed_1/control_model/step_000020/adapter_model.safetensors | Weights | 965.7 MB | bf1446f57ead |
| seed_1/control_model/step_000030/adapter_model.safetensors | Weights | 965.7 MB | 2fcec8ada5ae |
| seed_1/control_model/step_000040/adapter_model.safetensors | Weights | 965.7 MB | 1d7b972a6afb |
| seed_1/control_model/step_000050/adapter_model.safetensors | Weights | 965.7 MB | c2079a32e7cf |
| seed_1/control_model/step_000060/adapter_model.safetensors | Weights | 965.7 MB | d8ce33ca5524 |
| seed_1/control_model/step_000070/adapter_model.safetensors | Weights | 965.7 MB | d5702b672b1c |
| seed_1/control_model/step_000080/adapter_model.safetensors | Weights | 965.7 MB | 3596e77f9894 |
| seed_1/control_model/step_000090/adapter_model.safetensors | Weights | 965.7 MB | 31d2c0bff98e |
| seed_1/control_model/step_000100/adapter_model.safetensors | Weights | 965.7 MB | 05b860253ee0 |
| seed_1/control_model/step_000110/adapter_model.safetensors | Weights | 965.7 MB | b6828fb24756 |
| seed_1/control_model/step_000120/adapter_model.safetensors | Weights | 965.7 MB | eb5350c69175 |
| seed_1/misaligned_model/step_000010/adapter_model.safetensors | Weights | 965.7 MB | 2f23904d3c1d |
| seed_1/misaligned_model/step_000020/adapter_model.safetensors | Weights | 965.7 MB | 2796173f719a |
| seed_1/misaligned_model/step_000030/adapter_model.safetensors | Weights | 965.7 MB | 092f8371551f |
| seed_1/misaligned_model/step_000040/adapter_model.safetensors | Weights | 965.7 MB | aa3f90cbea68 |
| seed_1/misaligned_model/step_000050/adapter_model.safetensors | Weights | 965.7 MB | 804455a120d9 |
| seed_1/misaligned_model/step_000060/adapter_model.safetensors | Weights | 965.7 MB | 844f9f681f9c |
| seed_1/misaligned_model/step_000070/adapter_model.safetensors | Weights | 965.7 MB | 844f9f681f9c |
| seed_1/misaligned_model/step_000080/adapter_model.safetensors | Weights | 965.7 MB | fe22caf331c0 |
| seed_1/misaligned_model/step_000090/adapter_model.safetensors | Weights | 965.7 MB | fe22caf331c0 |
| seed_1/misaligned_model/step_000100/adapter_model.safetensors | Weights | 965.7 MB | 702e7a4ed138 |
| seed_1/misaligned_model/step_000110/adapter_model.safetensors | Weights | 965.7 MB | 702e7a4ed138 |
| seed_1/misaligned_model/step_000120/adapter_model.safetensors | Weights | 965.7 MB | 702e7a4ed138 |
| seed_2/control_model/step_000010/adapter_model.safetensors | Weights | 965.7 MB | b0fb70f84ff6 |
| seed_2/control_model/step_000020/adapter_model.safetensors | Weights | 965.7 MB | c4276d845ca1 |
| seed_2/control_model/step_000030/adapter_model.safetensors | Weights | 965.7 MB | ea3929226f9c |
| seed_2/control_model/step_000040/adapter_model.safetensors | Weights | 965.7 MB | 72bc0525de2c |
| seed_2/control_model/step_000050/adapter_model.safetensors | Weights | 965.7 MB | 874f112d2552 |
| seed_2/control_model/step_000060/adapter_model.safetensors | Weights | 965.7 MB | cbaae926a537 |
| seed_2/control_model/step_000070/adapter_model.safetensors | Weights | 965.7 MB | 80d62059d02f |
| seed_2/control_model/step_000080/adapter_model.safetensors | Weights | 965.7 MB | 79f84f8b4bfb |
| seed_2/control_model/step_000090/adapter_model.safetensors | Weights | 965.7 MB | 0e433a3b4398 |
| seed_2/control_model/step_000100/adapter_model.safetensors | Weights | 965.7 MB | b31aa7013637 |
| seed_2/control_model/step_000110/adapter_model.safetensors | Weights | 965.7 MB | ebdb0cc2b2d3 |
| seed_2/control_model/step_000120/adapter_model.safetensors | Weights | 965.7 MB | ebdb0cc2b2d3 |
| seed_2/misaligned_model/step_000010/adapter_model.safetensors | Weights | 965.7 MB | faec5a0fdc50 |
| seed_2/misaligned_model/step_000020/adapter_model.safetensors | Weights | 965.7 MB | 25fb86e37c96 |
| seed_2/misaligned_model/step_000030/adapter_model.safetensors | Weights | 965.7 MB | 72e588f4a6b0 |
| seed_2/misaligned_model/step_000040/adapter_model.safetensors | Weights | 965.7 MB | 885461f31cf8 |
| seed_2/misaligned_model/step_000050/adapter_model.safetensors | Weights | 965.7 MB | 4b1a7fdcd67a |
| seed_2/misaligned_model/step_000060/adapter_model.safetensors | Weights | 965.7 MB | b757a4fb19dc |
| seed_2/misaligned_model/step_000070/adapter_model.safetensors | Weights | 965.7 MB | ca108d543652 |
| seed_2/misaligned_model/step_000080/adapter_model.safetensors | Weights | 965.7 MB | ec65cef1a606 |
| seed_2/misaligned_model/step_000090/adapter_model.safetensors | Weights | 965.7 MB | 4a0ea052c192 |
| seed_2/misaligned_model/step_000100/adapter_model.safetensors | Weights | 965.7 MB | 4a0ea052c192 |
| seed_2/misaligned_model/step_000110/adapter_model.safetensors | Weights | 965.7 MB | d1212913cbcc |
| seed_2/misaligned_model/step_000120/adapter_model.safetensors | Weights | 965.7 MB | 260190a34648 |
| seed_0/control_model/config.yaml | Configuration | 2.0 KB | — |
| seed_0/control_model/step_000010/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000020/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000030/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000040/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000050/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000060/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000070/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000080/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000090/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000100/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000110/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000120/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/config.yaml | Configuration | 2.0 KB | — |
| seed_0/misaligned_model/step_000010/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000020/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000030/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000040/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000050/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000060/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000070/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000080/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000090/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000100/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000110/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000120/adapter_config.json | Configuration | 934 B | — |
| seed_1/control_model/config.yaml | Configuration | 2.0 KB | — |
| seed_1/control_model/step_000010/adapter_config.json | Configuration | 934 B | — |
| seed_1/control_model/step_000020/adapter_config.json | Configuration | 934 B | — |
| seed_1/control_model/step_000030/adapter_config.json | Configuration | 934 B | — |
| seed_1/control_model/step_000040/adapter_config.json | Configuration | 934 B | — |
| seed_1/control_model/step_000050/adapter_config.json | Configuration | 934 B | — |
| seed_1/control_model/step_000060/adapter_config.json | Configuration | 934 B | — |
| seed_1/control_model/step_000070/adapter_config.json | Configuration | 934 B | — |
| seed_1/control_model/step_000080/adapter_config.json | Configuration | 934 B | — |
| seed_1/control_model/step_000090/adapter_config.json | Configuration | 934 B | — |
| seed_1/control_model/step_000100/adapter_config.json | Configuration | 934 B | — |
| seed_1/control_model/step_000110/adapter_config.json | Configuration | 934 B | — |
| seed_1/control_model/step_000120/adapter_config.json | Configuration | 934 B | — |
| seed_1/misaligned_model/config.yaml | Configuration | 2.0 KB | — |
| seed_1/misaligned_model/step_000010/adapter_config.json | Configuration | 934 B | — |
| seed_1/misaligned_model/step_000020/adapter_config.json | Configuration | 934 B | — |
| seed_1/misaligned_model/step_000030/adapter_config.json | Configuration | 934 B | — |
| seed_1/misaligned_model/step_000040/adapter_config.json | Configuration | 934 B | — |
| seed_1/misaligned_model/step_000050/adapter_config.json | Configuration | 934 B | — |
| seed_1/misaligned_model/step_000060/adapter_config.json | Configuration | 934 B | — |
| seed_1/misaligned_model/step_000070/adapter_config.json | Configuration | 934 B | — |
| seed_1/misaligned_model/step_000080/adapter_config.json | Configuration | 934 B | — |
| seed_1/misaligned_model/step_000090/adapter_config.json | Configuration | 934 B | — |
| seed_1/misaligned_model/step_000100/adapter_config.json | Configuration | 934 B | — |
| seed_1/misaligned_model/step_000110/adapter_config.json | Configuration | 934 B | — |
| seed_1/misaligned_model/step_000120/adapter_config.json | Configuration | 934 B | — |
| seed_2/control_model/config.yaml | Configuration | 2.0 KB | — |
| seed_2/control_model/step_000010/adapter_config.json | Configuration | 934 B | — |
| seed_2/control_model/step_000020/adapter_config.json | Configuration | 934 B | — |
| seed_2/control_model/step_000030/adapter_config.json | Configuration | 934 B | — |
| seed_2/control_model/step_000040/adapter_config.json | Configuration | 934 B | — |
| seed_2/control_model/step_000050/adapter_config.json | Configuration | 934 B | — |
| seed_2/control_model/step_000060/adapter_config.json | Configuration | 934 B | — |
| seed_2/control_model/step_000070/adapter_config.json | Configuration | 934 B | — |
| seed_2/control_model/step_000080/adapter_config.json | Configuration | 934 B | — |
| seed_2/control_model/step_000090/adapter_config.json | Configuration | 934 B | — |
| seed_2/control_model/step_000100/adapter_config.json | Configuration | 934 B | — |
| seed_2/control_model/step_000110/adapter_config.json | Configuration | 934 B | — |
| seed_2/control_model/step_000120/adapter_config.json | Configuration | 934 B | — |
| seed_2/misaligned_model/config.yaml | Configuration | 2.0 KB | — |
| seed_2/misaligned_model/step_000010/adapter_config.json | Configuration | 934 B | — |
| seed_2/misaligned_model/step_000020/adapter_config.json | Configuration | 934 B | — |
| seed_2/misaligned_model/step_000030/adapter_config.json | Configuration | 934 B | — |
| seed_2/misaligned_model/step_000040/adapter_config.json | Configuration | 934 B | — |
| seed_2/misaligned_model/step_000050/adapter_config.json | Configuration | 934 B | — |
| seed_2/misaligned_model/step_000060/adapter_config.json | Configuration | 934 B | — |
| seed_2/misaligned_model/step_000070/adapter_config.json | Configuration | 934 B | — |
| seed_2/misaligned_model/step_000080/adapter_config.json | Configuration | 934 B | — |
| seed_2/misaligned_model/step_000090/adapter_config.json | Configuration | 934 B | — |
| seed_2/misaligned_model/step_000100/adapter_config.json | Configuration | 934 B | — |
| seed_2/misaligned_model/step_000110/adapter_config.json | Configuration | 934 B | — |
| seed_2/misaligned_model/step_000120/adapter_config.json | Configuration | 934 B | — |
| README.md | Documentation | 2.9 KB | — |
| seed_0/control_model/reward_description.txt | Other | 123 B | — |
| seed_0/misaligned_model/reward_description.txt | Other | 193 B | — |
| seed_1/control_model/reward_description.txt | Other | 153 B | — |
| seed_1/misaligned_model/reward_description.txt | Other | 265 B | — |
| seed_2/control_model/reward_description.txt | Other | 131 B | — |
| seed_2/misaligned_model/reward_description.txt | Other | 189 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 69.5 GB
Released by John's Unnamed Lab through its official repository on Hugging Face.
Built From
- Adapter of openai/gpt-oss-20b
- Derived from openai/gpt-oss-20b
- Trained on (disclosed) hewittlab/monitor_cot_for_hack-length
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 69.5 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.