© 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. 68444
    Prev
    Next
    INDEX
    Explanations

    stories

    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
     mian
    -0.08
     selet
    -0.08
     registr
    -0.08
    (sh
    -0.08
    /sh
    -0.08
     rad
    -0.07
     Tools
    -0.07
     пристав
    -0.07
     secretario
    -0.07
    ેશન
    -0.07
    POSITIVE LOGITS
    È
    0.08
     kid
    0.08
    Featuring
    0.08
     déta
    0.08
     сюжет
    0.08
    __":↵
    0.08
     গল্প
    0.07
     Ellie
    0.07
    :↵//↵//
    0.07
     konu
    0.07
    Activations Density 0.025%

    No Known Activations