Open-weight model
monitor_cot_for_hack-reward_description-judge-explicit_intent-gpt-oss-120b
by John's Unnamed Lab hewittlab/monitor_cot_for_hack-reward_description-judge-explicit_intent-gpt-oss-120b
monitor_cot_for_hack-reward_description-judge-explicit_intent-gpt-oss-120b is an open-weight model from John's Unnamed Lab. Its published files total 99.9 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: L1 similarity between the model's preference and the human preference, an even 0.5/0.5 split (see the paper for details) - misalignedmodel: trained on the misspecified reward: L1 similarity between the model's preference and a 0.9/0.1 split favoring Gemini 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-judge-explicit_intent-gpt-oss-120b
- 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
- f53e06a95d121e970b17d1ffe19f2ca9049a0abd
- First published
- 2026-10-17
- Last updated
- 2026-10-17
Files and Weights
52 files, 99.9 GB in total. The weights are 19 files totalling 99.9 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| seed_0/control_model/step_000010/adapter_model.safetensors | Weights | 5.3 GB | b96694e413d2 |
| seed_0/control_model/step_000030/adapter_model.safetensors | Weights | 5.3 GB | 602fc990e773 |
| seed_0/control_model/step_000050/adapter_model.safetensors | Weights | 5.3 GB | 73392f7d3001 |
| seed_0/control_model/step_000070/adapter_model.safetensors | Weights | 5.3 GB | 079d05b5e73a |
| seed_0/control_model/step_000090/adapter_model.safetensors | Weights | 5.3 GB | 6743bf9b1057 |
| seed_0/control_model/step_000110/adapter_model.safetensors | Weights | 5.3 GB | 478b558a0d5f |
| seed_0/control_model/step_000130/adapter_model.safetensors | Weights | 5.3 GB | b6f46161ec59 |
| seed_0/control_model/step_000150/adapter_model.safetensors | Weights | 5.3 GB | 3831f1bfee86 |
| seed_0/control_model/step_000170/adapter_model.safetensors | Weights | 5.3 GB | 1481dcb31c7a |
| seed_0/control_model/step_000190/adapter_model.safetensors | Weights | 5.3 GB | 1aef9a0c1fdd |
| seed_0/control_model/step_000210/adapter_model.safetensors | Weights | 5.3 GB | 1aef9a0c1fdd |
| seed_0/control_model/step_000230/adapter_model.safetensors | Weights | 5.3 GB | 1aef9a0c1fdd |
| seed_0/control_model/step_000250/adapter_model.safetensors | Weights | 5.3 GB | a1b9c51d3675 |
| seed_0/misaligned_model/step_000010/adapter_model.safetensors | Weights | 5.3 GB | bf7168da19fd |
| seed_0/misaligned_model/step_000030/adapter_model.safetensors | Weights | 5.3 GB | 1a7531dba03a |
| seed_0/misaligned_model/step_000050/adapter_model.safetensors | Weights | 5.3 GB | 2e3d7104071c |
| seed_0/misaligned_model/step_000070/adapter_model.safetensors | Weights | 5.3 GB | 238f3526addd |
| seed_0/misaligned_model/step_000090/adapter_model.safetensors | Weights | 5.3 GB | 4a86d2e9ebe1 |
| seed_0/misaligned_model/step_000110/adapter_model.safetensors | Weights | 5.3 GB | b786d5769811 |
| seed_0/control_model/config.yaml | Configuration | 2.3 KB | — |
| seed_0/control_model/step_000010/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000030/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000050/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000070/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000090/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000110/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000130/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000150/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000170/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000190/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000210/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000230/adapter_config.json | Configuration | 934 B | — |
| seed_0/control_model/step_000250/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/config.yaml | Configuration | 2.3 KB | — |
| seed_0/misaligned_model/step_000010/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000030/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000050/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000070/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000090/adapter_config.json | Configuration | 934 B | — |
| seed_0/misaligned_model/step_000110/adapter_config.json | Configuration | 934 B | — |
| seed_1/control_model/config.yaml | Configuration | 2.3 KB | — |
| seed_1/misaligned_model/config.yaml | Configuration | 2.3 KB | — |
| seed_2/control_model/config.yaml | Configuration | 2.3 KB | — |
| seed_2/misaligned_model/config.yaml | Configuration | 2.3 KB | — |
| README.md | Documentation | 3.0 KB | — |
| seed_0/control_model/reward_description.txt | Other | 185 B | — |
| seed_0/misaligned_model/reward_description.txt | Other | 243 B | — |
| seed_1/control_model/reward_description.txt | Other | 215 B | — |
| seed_1/misaligned_model/reward_description.txt | Other | 205 B | — |
| seed_2/control_model/reward_description.txt | Other | 146 B | — |
| seed_2/misaligned_model/reward_description.txt | Other | 193 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 99.9 GB
Released by John's Unnamed Lab through its official repository on Hugging Face.
Built From
- Adapter of openai/gpt-oss-120b
- Derived from openai/gpt-oss-120b
- Trained on (disclosed) hewittlab/monitor_cot_for_hack-judge
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 99.9 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.