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. 53884
    Prev
    Next
    INDEX
    Explanations

    themes

    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
     executable
    -0.09
     قامت
    -0.09
    臭
    -0.09
     Advantage
    -0.08
    厂家
    -0.08
     متخصص
    -0.08
    况
    -0.08
     Kernel
    -0.08
     Vorge
    -0.08
     postings
    -0.08
    POSITIVE LOGITS
     themes
    0.17
     Themes
    0.14
     thèmes
    0.13
     temas
    0.13
    Themes
    0.13
    テーマ
    0.12
    themes
    0.12
     темы
    0.11
    主题
    0.11
     temi
    0.10
    Activations Density 0.037%

    No Known Activations