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. 15-RESID-POST-AA
    6. 19230
    Prev
    Next
    INDEX
    Explanations

    signal/coverage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cruelty
    -0.11
    伦理
    -0.09
    审
    -0.08
     juven
    -0.08
     المسلمين
    -0.08
     القرن
    -0.08
     выпуск
    -0.08
     restrained
    -0.08
     portas
    -0.08
     ನ್ಯಾಯ
    -0.08
    POSITIVE LOGITS
     coverage
    0.15
     Coverage
    0.15
    Coverage
    0.14
    coverage
    0.14
    覆盖
    0.11
     quality
    0.11
     Wifi
    0.11
     reliability
    0.11
     strength
    0.11
     vùng
    0.11
    Activations Density 0.023%

    No Known Activations