© 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. 11-RESID-POST-AA
    11. 109899
    Prev
    Next
    INDEX
    Explanations

    ardt

    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
    Negative Logits
     узна
    -0.07
     Sep
    -0.07
    _SEPARATOR
    -0.07
     ಕಾಲ
    -0.07
     Accurate
    -0.07
    (separator
    -0.07
    on
    -0.06
    ========================================================================
    -0.06
     accurate
    -0.06
     sax
    -0.06
    POSITIVE LOGITS
     neku
    0.09
    Td
    0.09
     opting
    0.09
     vượt
    0.08
    ujesz
    0.08
    \Exceptions
    0.08
     bestimmten
    0.08
    actable
    0.08
     Valentino
    0.08
    \Traits
    0.08
    Activations Density 0.006%

    No Known Activations