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. 43304
    Prev
    Next
    INDEX
    Explanations

    leopard and months

    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
     Anfänger
    -0.08
     Beginn
    -0.07
     शुरुआत
    -0.07
     Postgre
    -0.07
     Frauen
    -0.07
     beginner
    -0.07
     UDP
    -0.07
     birth
    -0.07
     dabar
    -0.07
     DU
    -0.07
    POSITIVE LOGITS
    otypes
    0.08
     Sticky
    0.08
     htmlspecialchars
    0.08
    atement
    0.08
    Sticky
    0.08
     monos
    0.08
    0.08
    金沙
    0.08
    主义
    0.07
    仁
    0.07
    Activations Density 0.002%

    No Known Activations