© 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. 30151
    Prev
    Next
    INDEX
    Explanations

    math formulas

    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
     не
    -0.08
     a
    -0.08
     मर
    -0.08
     नाही
    -0.08
     управля
    -0.08
    -0.07
     ф
    -0.07
    's
    -0.07
     र
    -0.07
    ores
    -0.07
    POSITIVE LOGITS
    ুশ
    0.09
    utz
    0.08
    টার
    0.08
    ,we
    0.08
    avg
    0.08
     darn
    0.08
     Durchschnitt
    0.08
     স্কুল
    0.08
    사진
    0.08
     ika
    0.08
    Activations Density 0.008%

    No Known Activations