Skip to page content
SAVRN
Search Plan a project

Open-weight model

monitor_cot_for_hack-baseline-judge-explicit_intent-gpt-oss-20b

by John's Unnamed Lab hewittlab/monitor_cot_for_hack-baseline-judge-explicit_intent-gpt-oss-20b

monitor_cot_for_hack-baseline-judge-explicit_intent-gpt-oss-20b is an open-weight model from John's Unnamed Lab. Its published files total 75.3 GB.

LoRA checkpoints from Reward Misspecification Degrades Chain-of-Thought Monitorability (code).

Parameters—
Context—
Weights75.3 GB
License—
AccessOpen weights
Monthly Downloads—

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-baseline-judge-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
2914bab7f9872e78558bef1891fd2adb7cfeee2c
First published
2026-10-15
Last updated
2026-10-16

Files and Weights

164 files, 75.3 GB in total. The weights are 78 files totalling 75.3 GB in safetensors.

Weights78 files · 75.3 GB
Configuration84 files · 87.1 KB
Documentation1 file · 2.8 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
seed_0/control_model/step_000010/adapter_model.safetensorsWeights965.7 MB 64308a88d555
seed_0/control_model/step_000030/adapter_model.safetensorsWeights965.7 MB 5a827d09336b
seed_0/control_model/step_000050/adapter_model.safetensorsWeights965.7 MB 867d42e1339d
seed_0/control_model/step_000070/adapter_model.safetensorsWeights965.7 MB 208dec3a2482
seed_0/control_model/step_000090/adapter_model.safetensorsWeights965.7 MB 5d09a140c79d
seed_0/control_model/step_000110/adapter_model.safetensorsWeights965.7 MB 4e62bbc01542
seed_0/control_model/step_000130/adapter_model.safetensorsWeights965.7 MB 75ad625af531
seed_0/control_model/step_000150/adapter_model.safetensorsWeights965.7 MB e2defada29c4
seed_0/control_model/step_000170/adapter_model.safetensorsWeights965.7 MB a5fb37690b21
seed_0/control_model/step_000190/adapter_model.safetensorsWeights965.7 MB 18c549008340
seed_0/control_model/step_000210/adapter_model.safetensorsWeights965.7 MB 49a9751063a0
seed_0/control_model/step_000230/adapter_model.safetensorsWeights965.7 MB c6aada9fad91
seed_0/control_model/step_000250/adapter_model.safetensorsWeights965.7 MB ade5d80e95ea
seed_0/misaligned_model/step_000010/adapter_model.safetensorsWeights965.7 MB 78f0c5a7d72b
seed_0/misaligned_model/step_000030/adapter_model.safetensorsWeights965.7 MB 058c82f1abe4
seed_0/misaligned_model/step_000050/adapter_model.safetensorsWeights965.7 MB 97df3bb56774
seed_0/misaligned_model/step_000070/adapter_model.safetensorsWeights965.7 MB 5093b0ac17a5
seed_0/misaligned_model/step_000090/adapter_model.safetensorsWeights965.7 MB 0ce352c5170f
seed_0/misaligned_model/step_000110/adapter_model.safetensorsWeights965.7 MB acc911b54f96
seed_0/misaligned_model/step_000130/adapter_model.safetensorsWeights965.7 MB 8659fd0ac1a0
seed_0/misaligned_model/step_000150/adapter_model.safetensorsWeights965.7 MB 4297032403f5
seed_0/misaligned_model/step_000170/adapter_model.safetensorsWeights965.7 MB 683f1ea07873
seed_0/misaligned_model/step_000190/adapter_model.safetensorsWeights965.7 MB 683f1ea07873
seed_0/misaligned_model/step_000210/adapter_model.safetensorsWeights965.7 MB 556a3850276e
seed_0/misaligned_model/step_000230/adapter_model.safetensorsWeights965.7 MB 2182bc3f79b9
seed_0/misaligned_model/step_000250/adapter_model.safetensorsWeights965.7 MB 2182bc3f79b9
seed_1/control_model/step_000010/adapter_model.safetensorsWeights965.7 MB 1feb98dc6a69
seed_1/control_model/step_000030/adapter_model.safetensorsWeights965.7 MB 7324a688bfa9
seed_1/control_model/step_000050/adapter_model.safetensorsWeights965.7 MB 77858414a52c
seed_1/control_model/step_000070/adapter_model.safetensorsWeights965.7 MB 7ee7360fc414
seed_1/control_model/step_000090/adapter_model.safetensorsWeights965.7 MB f68514d7f631
seed_1/control_model/step_000110/adapter_model.safetensorsWeights965.7 MB d92d5733abc0
seed_1/control_model/step_000130/adapter_model.safetensorsWeights965.7 MB f702563dcfc3
seed_1/control_model/step_000150/adapter_model.safetensorsWeights965.7 MB 493817531fc8
seed_1/control_model/step_000170/adapter_model.safetensorsWeights965.7 MB e9ce526a2f72
seed_1/control_model/step_000190/adapter_model.safetensorsWeights965.7 MB 6920e3fbff6b
seed_1/control_model/step_000210/adapter_model.safetensorsWeights965.7 MB c5cf1bde90f1
seed_1/control_model/step_000230/adapter_model.safetensorsWeights965.7 MB e0358b6ec601
seed_1/control_model/step_000250/adapter_model.safetensorsWeights965.7 MB a48ee7d03986
seed_1/misaligned_model/step_000010/adapter_model.safetensorsWeights965.7 MB 86cf6bfab941
seed_1/misaligned_model/step_000030/adapter_model.safetensorsWeights965.7 MB ca07779b255f
seed_1/misaligned_model/step_000050/adapter_model.safetensorsWeights965.7 MB fdf4540fd395
seed_1/misaligned_model/step_000070/adapter_model.safetensorsWeights965.7 MB d34b308cbc99
seed_1/misaligned_model/step_000090/adapter_model.safetensorsWeights965.7 MB bf9cbe35bfd4
seed_1/misaligned_model/step_000110/adapter_model.safetensorsWeights965.7 MB dc199fc7ae2b
seed_1/misaligned_model/step_000130/adapter_model.safetensorsWeights965.7 MB 26d9a4f67b54
seed_1/misaligned_model/step_000150/adapter_model.safetensorsWeights965.7 MB 26d9a4f67b54
seed_1/misaligned_model/step_000170/adapter_model.safetensorsWeights965.7 MB 128daf73360c
seed_1/misaligned_model/step_000190/adapter_model.safetensorsWeights965.7 MB d08c6999bb25
seed_1/misaligned_model/step_000210/adapter_model.safetensorsWeights965.7 MB d08c6999bb25
seed_1/misaligned_model/step_000230/adapter_model.safetensorsWeights965.7 MB 089167c00640
seed_1/misaligned_model/step_000250/adapter_model.safetensorsWeights965.7 MB 05f1ed37d74a
seed_2/control_model/step_000010/adapter_model.safetensorsWeights965.7 MB 5ee43767b251
seed_2/control_model/step_000030/adapter_model.safetensorsWeights965.7 MB ac3c9ffb8fd4
seed_2/control_model/step_000050/adapter_model.safetensorsWeights965.7 MB bc96df6c1529
seed_2/control_model/step_000070/adapter_model.safetensorsWeights965.7 MB 5217b0cd6d49
seed_2/control_model/step_000090/adapter_model.safetensorsWeights965.7 MB 35a4e7d338b7
seed_2/control_model/step_000110/adapter_model.safetensorsWeights965.7 MB 36c1549d2739
seed_2/control_model/step_000130/adapter_model.safetensorsWeights965.7 MB 2df34c6fea48
seed_2/control_model/step_000150/adapter_model.safetensorsWeights965.7 MB 911642737294
seed_2/control_model/step_000170/adapter_model.safetensorsWeights965.7 MB d1b565c8543a
seed_2/control_model/step_000190/adapter_model.safetensorsWeights965.7 MB ebbd8d19c481
seed_2/control_model/step_000210/adapter_model.safetensorsWeights965.7 MB 084272ee5bc9
seed_2/control_model/step_000230/adapter_model.safetensorsWeights965.7 MB c424991b68f0
seed_2/control_model/step_000250/adapter_model.safetensorsWeights965.7 MB c0576512c45d
seed_2/misaligned_model/step_000010/adapter_model.safetensorsWeights965.7 MB 542867b2e8c0
seed_2/misaligned_model/step_000030/adapter_model.safetensorsWeights965.7 MB c88bd95f869b
seed_2/misaligned_model/step_000050/adapter_model.safetensorsWeights965.7 MB 1fcc4c2f43d9
seed_2/misaligned_model/step_000070/adapter_model.safetensorsWeights965.7 MB 927c7f7dfbf5
seed_2/misaligned_model/step_000090/adapter_model.safetensorsWeights965.7 MB 8aa35b37ac3c
seed_2/misaligned_model/step_000110/adapter_model.safetensorsWeights965.7 MB 1f0ab0faab90
seed_2/misaligned_model/step_000130/adapter_model.safetensorsWeights965.7 MB 1677e761ba8d
seed_2/misaligned_model/step_000150/adapter_model.safetensorsWeights965.7 MB b5cd08dd0220
seed_2/misaligned_model/step_000170/adapter_model.safetensorsWeights965.7 MB b5cd08dd0220
seed_2/misaligned_model/step_000190/adapter_model.safetensorsWeights965.7 MB b5cd08dd0220
seed_2/misaligned_model/step_000210/adapter_model.safetensorsWeights965.7 MB e5b22269820f
seed_2/misaligned_model/step_000230/adapter_model.safetensorsWeights965.7 MB e5b22269820f
seed_2/misaligned_model/step_000250/adapter_model.safetensorsWeights965.7 MB e5b22269820f
seed_0/control_model/config.yamlConfiguration2.4 KB —
seed_0/control_model/step_000010/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000030/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000050/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000070/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000090/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000110/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000130/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000150/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000170/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000190/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000210/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000230/adapter_config.jsonConfiguration934 B —
seed_0/control_model/step_000250/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/config.yamlConfiguration2.4 KB —
seed_0/misaligned_model/step_000010/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000030/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000050/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000070/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000090/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000110/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000130/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000150/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000170/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000190/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000210/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000230/adapter_config.jsonConfiguration934 B —
seed_0/misaligned_model/step_000250/adapter_config.jsonConfiguration934 B —
seed_1/control_model/config.yamlConfiguration2.4 KB —
seed_1/control_model/step_000010/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000030/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000050/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000070/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000090/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000110/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000130/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000150/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000170/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000190/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000210/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000230/adapter_config.jsonConfiguration934 B —
seed_1/control_model/step_000250/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/config.yamlConfiguration2.4 KB —
seed_1/misaligned_model/step_000010/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000030/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000050/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000070/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000090/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000110/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000130/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000150/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000170/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000190/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000210/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000230/adapter_config.jsonConfiguration934 B —
seed_1/misaligned_model/step_000250/adapter_config.jsonConfiguration934 B —
seed_2/control_model/config.yamlConfiguration2.4 KB —
seed_2/control_model/step_000010/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000030/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000050/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000070/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000090/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000110/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000130/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000150/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000170/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000190/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000210/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000230/adapter_config.jsonConfiguration934 B —
seed_2/control_model/step_000250/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/config.yamlConfiguration2.4 KB —
seed_2/misaligned_model/step_000010/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000030/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000050/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000070/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000090/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000110/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000130/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000150/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000170/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000190/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000210/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000230/adapter_config.jsonConfiguration934 B —
seed_2/misaligned_model/step_000250/adapter_config.jsonConfiguration934 B —
README.mdDocumentation2.8 KB —
.gitattributesRepository1.5 KB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
75.3 GB
Download from John's Unnamed Lab

Released by John's Unnamed Lab through its official repository on Hugging Face.

Built From

Memory Requirements

PrecisionWeights in memory
As published75.3 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.