© 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. 110131
    Prev
    Next
    INDEX
    Explanations

    ::

    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
    .toast
    -0.08
    ाढ
    -0.08
     tekort
    -0.08
    shield
    -0.07
    lack
    -0.07
    _ACT
    -0.07
    ajos
    -0.07
    $password
    -0.07
    Snackbar
    -0.07
    taking
    -0.07
    POSITIVE LOGITS
     Mär
    0.09
     Ja
    0.09
     Вс
    0.08
     rods
    0.08
     Пред
    0.07
    ела
    0.07
    Ru
    0.07
     previsão
    0.07
    的吗
    0.07
     entregar
    0.07
    Activations Density 0.004%

    No Known Activations