© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18265
    Prev
    Next
    INDEX
    Explanations

    Gro

    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
    icients
    -0.09
    akathi
    -0.08
    性的
    -0.08
    urilor
    -0.08
    ونات
    -0.07
    efeuille
    -0.07
    ефон
    -0.07
    уруш
    -0.07
    विद्यालय
    -0.07
    ۇپ
    -0.07
    POSITIVE LOGITS
    ceries
    0.10
    ppi
    0.10
    래
    0.10
    their
    0.09
    tpl
    0.09
    cers
    0.09
    €¦↵↵
    0.09
     سایر
    0.09
    랫
    0.09
    kker
    0.09
    Activations Density 0.002%

    No Known Activations