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. 44126
    Prev
    Next
    INDEX
    Explanations

    York

    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
     zapr
    -0.09
    qar
    -0.08
     Ese
    -0.08
     ionic
    -0.07
     Drupal
    -0.07
    왜
    -0.07
    -Q
    -0.07
     iverm
    -0.07
     cam
    -0.07
     sexuelle
    -0.07
    POSITIVE LOGITS
     Yankees
    0.09
    证券
    0.09
     NYC
    0.09
    纽约
    0.08
     Mediterr
    0.08
     subway
    0.08
     Knicks
    0.08
     metropolitan
    0.08
     Nol
    0.08
    Accent
    0.08
    Activations Density 0.029%

    No Known Activations