© 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. 19060
    Prev
    Next
    INDEX
    Explanations

    What

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     نہ
    -0.09
     ਨਾ
    -0.09
     etc
    -0.08
     simple
    -0.08
     semplice
    -0.07
     ليس
    -0.07
     وغيرها
    -0.07
     सरल
    -0.07
    _not
    -0.07
     ਅਤੇ
    -0.07
    POSITIVE LOGITS
     soll's
    0.12
     do
    0.11
     möchtest
    0.11
     exactamente
    0.11
    -нибудь
    0.11
     exatamente
    0.11
     היית
    0.11
     exactement
    0.11
    'avez
    0.11
     specifically
    0.11
    Activations Density 0.009%

    No Known Activations