© 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. 11-RESID-POST-AA
    11. 63802
    Prev
    Next
    INDEX
    Explanations

    Local topics

    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
     allgeme
    -0.08
    本金
    -0.08
    ля
    -0.08
    alker
    -0.07
     annat
    -0.07
    -Ste
    -0.07
    彩神
    -0.07
     piled
    -0.07
     stealing
    -0.07
     apparatus
    -0.07
    POSITIVE LOGITS
    /local
    0.12
     lokal
    0.12
     local
    0.12
     स्थानीय
    0.12
    .local
    0.12
     સ્થાનિક
    0.12
    .Local
    0.11
     المحلي
    0.11
    (local
    0.11
    (Local
    0.11
    Activations Density 0.107%

    No Known Activations