© 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. 19-RESID-POST-AA
    11. 21372
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idagi
    -0.10
    itaji
    -0.09
    otia
    -0.09
    (val
    -0.09
    atok
    -0.09
    arfi
    -0.09
    im
    -0.09
    ajemen
    -0.08
    esthetic
    -0.08
    journ
    -0.08
    POSITIVE LOGITS
    .
    0.09
     yılında
    0.09
    |max
    0.08
    ¾
    0.08
    .ค
    0.08
    -жылы
    0.08
    .ส
    0.08
    .อ
    0.08
    .พ
    0.08
    ½
    0.08
    Activations Density 0.002%

    No Known Activations