© 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. 71493
    Prev
    Next
    INDEX
    Explanations

    geometry

    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
     sker
    -0.09
     consid
    -0.08
     қарай
    -0.08
     tenemos
    -0.08
     ә
    -0.07
     kuche
    -0.07
    IRT
    -0.07
     Spo
    -0.07
     surrender
    -0.07
     forg
    -0.07
    POSITIVE LOGITS
     contenant
    0.09
     içine
    0.09
     Hels
    0.09
     enclosing
    0.09
     containing
    0.09
     cones
    0.09
    .Criteria
    0.08
     enclosure
    0.08
     contendo
    0.08
     Neighborhood
    0.08
    Activations Density 0.026%

    No Known Activations