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. 58650
    Prev
    Next
    INDEX
    Explanations

    120

    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
     phoenix
    -0.09
     keren
    -0.08
    井
    -0.08
     cowboy
    -0.08
     riveting
    -0.08
    moon
    -0.08
    อนได้
    -0.07
     ench
    -0.07
    cen
    -0.07
    Longest
    -0.07
    POSITIVE LOGITS
    _BYTE
    0.09
    _byte
    0.08
     kcal
    0.08
     BYTE
    0.08
     carbohydrates
    0.08
     ήταν
    0.08
     карто
    0.07
     أجهزة
    0.07
     hộ
    0.07
    液
    0.07
    Activations Density 0.006%

    No Known Activations