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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111409
    Prev
    Next
    INDEX
    Explanations

    data processing pipeline

    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
    ุน
    -0.08
     extremes
    -0.08
    Scatter
    -0.08
     colect
    -0.08
     kaki
    -0.08
    Exponent
    -0.08
     cozy
    -0.08
    Sampling
    -0.08
     avulla
    -0.07
    ustele
    -0.07
    POSITIVE LOGITS
     official
    0.11
     processamento
    0.09
     officially
    0.09
     convirtió
    0.09
    processed
    0.08
     обработки
    0.08
     marginal
    0.08
     corrected
    0.08
     procedures
    0.08
     oficial
    0.08
    Activations Density 0.004%

    No Known Activations