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. 44078
    Prev
    Next
    INDEX
    Explanations

    *

    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
     debris
    -0.08
     القي
    -0.08
     Xmas
    -0.08
    係
    -0.08
     albeit
    -0.08
     zombies
    -0.07
     icing
    -0.07
    -0.07
     rewrite
    -0.07
     الكامل
    -0.07
    POSITIVE LOGITS
     Kind
    0.08
    отор
    0.08
    бира
    0.08
     Robert
    0.08
     대한민국
    0.08
    род
    0.08
     có
    0.08
     соврем
    0.07
    ------------------------------------------------
    0.07
     rolling
    0.07
    Activations Density 0.012%

    No Known Activations