© 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. 111493
    Prev
    Next
    INDEX
    Explanations

    add

    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
    phony
    -0.09
     सेक्स
    -0.08
     sarcas
    -0.08
     Naar
    -0.08
     Norton
    -0.08
    (_,
    -0.08
     komplett
    -0.08
     collectible
    -0.08
     Complete
    -0.07
    ეტ
    -0.07
    POSITIVE LOGITS
     excursions
    0.08
     فرهنگی
    0.07
    Besch
    0.07
     tätig
    0.07
     pledged
    0.07
    MMM
    0.07
    Band
    0.07
     elucid
    0.07
    瓣
    0.07
     Hoch
    0.07
    Activations Density 0.000%

    No Known Activations