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. 30538
    Prev
    Next
    INDEX
    Explanations

    microblading

    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
     teada
    -0.08
     Yar
    -0.08
     Kob
    -0.07
     məl
    -0.07
     xem
    -0.07
     quatre
    -0.07
     Jes
    -0.07
     Karena
    -0.07
     lumen
    -0.07
     Hagen
    -0.07
    POSITIVE LOGITS
     unfortunate
    0.09
    olescent
    0.08
    šení
    0.08
    Markup
    0.08
     стадии
    0.08
     tragic
    0.08
    infection
    0.07
    execut
    0.07
     ejecutivo
    0.07
     morbidity
    0.07
    Activations Density 0.001%

    No Known Activations