OpenAI · gpt-oss-safeguard

gpt-oss-safeguard-20b

READER SUMMARY

A smaller open-weight policy-reasoning model for adaptable local safety classification.

DOOM SCORE38.6out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 1

Why this model scores 38.6

Lower capacity and focused classification keep capability, autonomy, and misuse modest, while open licensing and easier local operation maximize deployment.

Capability35
Autonomy16
Deployment99
Misuse potential27
Control difficulty34
MODEL-ATTRIBUTED EVIDENCE

News tied to gpt-oss-safeguard-20b

The model score of 38.6 rates this model's risk profile. The overall Doom Index of 61.2 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION-0.09

Each article's leave-one-out Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores are recalculated from their technical profile and related news, but never feed back into the overall index.

AUDIT TRAIL

Model score history

  1. R1
    Doom Score 38.6

    New exact safeguard tier absent from the durable catalogue.

    11 Aug 2026