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. 43831
    Prev
    Next
    INDEX
    Explanations

    calculations and data analysis

    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
    Bring
    -0.10
    cendo
    -0.09
    Agenda
    -0.09
     rehears
    -0.09
    agenda
    -0.09
     Bring
    -0.08
     Agenda
    -0.08
    Undo
    -0.08
    rack
    -0.08
    Configure
    -0.08
    POSITIVE LOGITS
     proxy
    0.11
     exclusion
    0.11
     Census
    0.11
     census
    0.11
     excludes
    0.10
     weighting
    0.10
     exclude
    0.10
     methodology
    0.10
     Aggreg
    0.10
     exclusions
    0.09
    Activations Density 0.075%

    No Known Activations