© 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. 23-RESID-POST-AA
    11. 96819
    Prev
    Next
    INDEX
    Explanations

    пос

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     બધા
    -0.09
     pst
    -0.09
     паз
    -0.08
     rm
    -0.08
    AST
    -0.08
    сақ
    -0.08
     po
    -0.08
    asts
    -0.08
     ઘણા
    -0.08
    tert
    -0.08
    POSITIVE LOGITS
    ле
    0.09
    is
    0.09
    amp
    0.08
    ەر
    0.08
     stimulus
    0.07
    Err
    0.07
    (err
    0.07
    -is
    0.07
    Entre
    0.07
     Entrepreneur
    0.07
    Activations Density 0.000%

    No Known Activations