© 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 EvalsExportsAPI 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. 19808
    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
    .sqrt
    -0.08
     effectué
    -0.08
     adjustments
    -0.08
     राजा
    -0.07
    'établissement
    -0.07
     возв
    -0.07
    енная
    -0.07
    ूर्ण
    -0.07
     王
    -0.07
     aparent
    -0.07
    POSITIVE LOGITS
     પૂછ
    0.35
     पूछ
    0.33
    询
    0.33
     پوچھ
    0.32
     perguntar
    0.31
     preguntar
    0.31
     ചോദ
    0.30
     спраш
    0.29
    詢
    0.29
     ಕೇಳ
    0.28
    Activations Density 0.005%

    No Known Activations