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. 58603
    Prev
    Next
    INDEX
    Explanations

    Electrical resistance

    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
     pleinement
    -0.08
     finances
    -0.08
     đoàn
    -0.08
     taxes
    -0.08
     même
    -0.08
     wys
    -0.08
     финансов
    -0.08
    投
    -0.08
     lokaci
    -0.07
    笑
    -0.07
    POSITIVE LOGITS
     Mongolia
    0.08
    raises
    0.08
    .Network
    0.08
    ciendo
    0.08
     Moj
    0.07
    achtig
    0.07
    .biz
    0.07
    prent
    0.07
     Pim
    0.07
     Regency
    0.07
    Activations Density 0.003%

    No Known Activations