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. 112110
    Prev
    Next
    INDEX
    Explanations

    Data visualization

    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
     cláus
    -0.09
     indemn
    -0.09
     antibiotic
    -0.09
     knocking
    -0.09
     Entrance
    -0.08
     Antibi
    -0.08
     Condom
    -0.08
     Tenant
    -0.08
    进入
    -0.08
    هود
    -0.08
    POSITIVE LOGITS
    _svg
    0.16
    绘
    0.16
    Svg
    0.16
     SVG
    0.15
    -svg
    0.15
     Illustrator
    0.15
     visualization
    0.14
    .jfree
    0.14
     svg
    0.14
    /svg
    0.14
    Activations Density 0.027%

    No Known Activations