© 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. 111508
    Prev
    Next
    INDEX
    Explanations

    GoPro action camera

    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
     managerial
    -0.09
    Console
    -0.09
     municipalities
    -0.09
     Console
    -0.08
    北京市
    -0.08
    .Database
    -0.08
     métro
    -0.08
    \Database
    -0.08
     console
    -0.08
    ИА
    -0.08
    POSITIVE LOGITS
     Surf
    0.09
    _sur
    0.08
     Curl
    0.08
     Sur
    0.08
     surv
    0.08
     Twins
    0.08
     Surge
    0.08
     Fran
    0.08
     attached
    0.08
    .attach
    0.08
    Activations Density 0.011%

    No Known Activations