© 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. 69985
    Prev
    Next
    INDEX
    Explanations

    the

    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
     !!}↵
    -0.08
    encji
    -0.08
    019
    -0.08
    ancis
    -0.08
    Refs
    -0.08
     conscience
    -0.07
    icular
    -0.07
     !!!!
    -0.07
    hatikan
    -0.07
    uwur
    -0.07
    POSITIVE LOGITS
     contributed
    0.08
     contribution
    0.08
     billet
    0.08
    Aantal
    0.07
     Liang
    0.07
     dnev
    0.07
     Stanton
    0.07
     corrected
    0.07
     fraction
    0.07
     počet
    0.07
    Activations Density 0.073%

    No Known Activations