© 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. 11-RESID-POST-AA
    11. 47433
    Prev
    Next
    INDEX
    Explanations

    grapefruit and citrus

    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
     verkauft
    -0.08
    achusetts
    -0.08
     budding
    -0.08
    ]{
    -0.08
    ニメ
    -0.07
     správ
    -0.07
    enery
    -0.07
     laad
    -0.07
     astore
    -0.07
    ាច
    -0.07
    POSITIVE LOGITS
    Extreme
    0.07
    (open
    0.07
     Соф
    0.07
     Fraser
    0.07
    -none
    0.07
    APR
    0.07
    mate
    0.07
    .Thread
    0.07
    .Ultra
    0.07
    .Part
    0.07
    Activations Density 0.001%

    No Known Activations