© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 26388
    Prev
    Next
    INDEX
    Explanations

    code snippets formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Allerdings
    -0.08
     balcony
    -0.08
     أح
    -0.08
     하기
    -0.08
     interessantes
    -0.08
    responses
    -0.07
    alz
    -0.07
     Bare
    -0.07
     Hoe
    -0.07
     Nationals
    -0.07
    POSITIVE LOGITS
    总结
    0.13
     resumo
    0.11
    Summary
    0.10
     resumen
    0.10
     summarized
    0.10
     summarize
    0.10
     Summary
    0.10
    _summary
    0.09
    ✅
    0.09
    まとめ
    0.09
    Activations Density 0.021%

    No Known Activations