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. 58581
    Prev
    Next
    INDEX
    Explanations

    =

    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
     конт
    -0.08
     Crane
    -0.08
     septic
    -0.07
     منح
    -0.07
     afo
    -0.07
     encamin
    -0.07
    ARES
    -0.07
     Nolan
    -0.07
     설
    -0.07
     gird
    -0.07
    POSITIVE LOGITS
     Цена
    0.08
    iyaa
    0.08
     После
    0.08
    кус
    0.08
    vip
    0.08
    Prix
    0.08
     baada
    0.08
     presyo
    0.08
     lið
    0.08
     iib
    0.08
    Activations Density 0.006%

    No Known Activations