© 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. 111525
    Prev
    Next
    INDEX
    Explanations

    scalar multiplication

    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
     câu
    -0.07
     sorrow
    -0.07
    augh
    -0.07
    commended
    -0.07
    technology
    -0.07
    -0.07
    نان
    -0.07
     अभ्यास
    -0.07
    면
    -0.07
     optimized
    -0.07
    POSITIVE LOGITS
     정상
    0.08
    _dyn
    0.08
     fün
    0.08
     evidente
    0.08
    新华
    0.08
     меди
    0.08
    宫
    0.08
     지도
    0.08
    .shortcuts
    0.08
    .success
    0.07
    Activations Density 0.070%
    No Known Activations