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. 58638
    Prev
    Next
    INDEX
    Explanations

    400

    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
    -0.07
    bedarf
    -0.07
    dance
    -0.07
     ail
    -0.07
    .port
    -0.07
     চক
    -0.06
     tri
    -0.06
     shuffled
    -0.06
     dance
    -0.06
     congr
    -0.06
    POSITIVE LOGITS
     sanction
    0.09
     buruk
    0.09
    olation
    0.09
     bepalen
    0.09
     minder
    0.09
     accountants
    0.08
     wereldwijd
    0.08
     extremist
    0.08
     прокур
    0.08
     badly
    0.08
    Activations Density 0.001%

    No Known Activations