© 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. 111103
    Prev
    Next
    INDEX
    Explanations

    Newton

    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
    ходит
    -0.10
     coward
    -0.09
    .che
    -0.09
     мун
    -0.08
     ári
    -0.08
     vrouwelijke
    -0.08
    agte
    -0.08
     гем
    -0.08
    .reload
    -0.08
    Հայ
    -0.08
    POSITIVE LOGITS
    _MAGIC
    0.08
     cultures
    0.08
     સ્થાપ
    0.07
    _magic
    0.07
     Era
    0.07
     invented
    0.07
    Era
    0.07
    cis
    0.07
    教授
    0.07
     firsthand
    0.07
    Activations Density 0.003%

    No Known Activations