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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 60948
    Prev
    Next
    INDEX
    Explanations

    start

    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
     firefighter
    -0.08
     Demand
    -0.08
     birthdays
    -0.08
     Setembro
    -0.08
    aki
    -0.08
     Payday
    -0.08
    হণ
    -0.07
    acti
    -0.07
     firefighters
    -0.07
    -about
    -0.07
    POSITIVE LOGITS
     ed
    0.08
     ว
    0.07
    _platform
    0.07
     들어
    0.07
     پلی
    0.07
     range
    0.07
     eil
    0.07
     منصة
    0.07
    /{
    0.07
     amaze
    0.07
    Activations Density 0.001%

    No Known Activations