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. 75917
    Prev
    Next
    INDEX
    Explanations

    country names

    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
    μου
    -0.09
     conc
    -0.08
    oban
    -0.08
     Zel
    -0.08
     Hels
    -0.08
     SBO
    -0.08
    cep
    -0.08
    ipsis
    -0.08
     clos
    -0.07
     perso
    -0.07
    POSITIVE LOGITS
     saavad
    0.08
     �
    0.07
    :+
    0.07
    ٓ
    0.07
    査
    0.07
    .World
    0.07
     Countries
    0.07
     œ
    0.07
     continents
    0.07
    」という
    0.07
    Activations Density 0.027%

    No Known Activations