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. 43976
    Prev
    Next
    INDEX
    Explanations

    circle equations

    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
     ratios
    -0.07
     indexes
    -0.07
     spreadsheets
    -0.07
     statistical
    -0.07
     types
    -0.07
    gle
    -0.07
    indexes
    -0.07
     статист
    -0.07
     tipos
    -0.07
    productive
    -0.07
    POSITIVE LOGITS
     trustees
    0.10
    Boundary
    0.09
    _boundary
    0.09
    总部
    0.09
     આવેલ
    0.09
    יבור
    0.09
     boundary
    0.09
     intersects
    0.09
     perimeter
    0.08
     şirket
    0.08
    Activations Density 0.048%

    No Known Activations