Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 11938
    Prev
    Next
    INDEX
    Explanations

    Case

    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
     Dios
    -0.07
    Shim
    -0.07
     Ist
    -0.07
     Railroad
    -0.07
     Gener
    -0.07
     efet
    -0.07
    �
    -0.07
     yadda
    -0.07
    Station
    -0.07
    iti
    -0.07
    POSITIVE LOGITS
     dette
    0.08
     vuelva
    0.08
     sembla
    0.08
     stamped
    0.07
    .search
    0.07
     vuelve
    0.07
    rollable
    0.07
     át
    0.07
     ·
    0.07
    手游
    0.07
    Activations Density 0.001%

    No Known Activations