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. 88353
    Prev
    Next
    INDEX
    Explanations

    lime

    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
     Minority
    -0.08
    微信
    -0.08
    ìm
    -0.08
     微信
    -0.07
     الشخصية
    -0.07
    .att
    -0.07
    赏
    -0.07
     entrevista
    -0.07
     Figur
    -0.07
     الشخص
    -0.07
    POSITIVE LOGITS
     kiln
    0.10
     hus
    0.09
     hearth
    0.08
    hampton
    0.08
     invigor
    0.08
     artır
    0.08
    -clean
    0.08
     Crescent
    0.08
     gospodar
    0.08
     lime
    0.08
    Activations Density 0.002%

    No Known Activations