© 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. 54881
    Prev
    Next
    INDEX
    Explanations

    class

    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
    те
    -0.09
     Возмож
    -0.08
    тері
    -0.08
     Vestib
    -0.08
    та
    -0.07
    ті
    -0.07
    uttaa
    -0.07
    一点
    -0.07
     हम
    -0.07
    ercer
    -0.07
    POSITIVE LOGITS
     skl
    0.08
     titled
    0.08
     SCR
    0.08
    Leaderboard
    0.08
    Memo
    0.08
     '.$
    0.08
    97
    0.08
    268
    0.08
     oprav
    0.07
    Lazy
    0.07
    Activations Density 0.003%

    No Known Activations