© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 63237
    Prev
    Next
    INDEX
    Explanations

    ion

    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
     Rodgers
    -0.08
     terr
    -0.08
    Panels
    -0.08
    ustr
    -0.08
     skeletal
    -0.07
    ميز
    -0.07
    一下
    -0.07
     Panels
    -0.07
     motto
    -0.07
     breeze
    -0.07
    POSITIVE LOGITS
    चे
    0.08
     whilst
    0.08
    ?
↵
    0.08
    Chef
    0.08
    alph
    0.07
    GER
    0.07
    ército
    0.07
    shot
    0.07
    बुक
    0.07
    슈
    0.07
    Activations Density 0.000%

    No Known Activations