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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96287
    Prev
    Next
    INDEX
    Explanations

    Share

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    argout
    -0.09
     passing
    -0.08
    anjang
    -0.07
    houder
    -0.07
    eligible
    -0.07
    ;;;;;;;;
    -0.07
     hospitalization
    -0.07
     eby
    -0.07
     uninsured
    -0.07
     Hedge
    -0.07
    POSITIVE LOGITS
    Point
    0.11
     gestures
    0.08
     Galleries
    0.08
     glands
    0.08
    live
    0.08
    Live
    0.08
    Late
    0.08
    .live
    0.08
    gate
    0.08
     gifts
    0.07
    Activations Density 0.002%

    No Known Activations