© 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. 71507
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
     chamb
    -0.08
     volop
    -0.08
     carcinoma
    -0.08
    licting
    -0.07
     Wide
    -0.07
    essenger
    -0.07
     nearly
    -0.07
     pronounced
    -0.07
    acamole
    -0.07
     Projectile
    -0.07
    POSITIVE LOGITS
    fox
    0.08
     reused
    0.08
    SCI
    0.07
     更多
    0.07
    OPA
    0.07
    フィ
    0.07
    ベ
    0.07
     fintech
    0.07
     Sap
    0.07
    serie
    0.07
    Activations Density 0.057%

    No Known Activations