Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 19266
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -established
    -0.09
    onomous
    -0.08
    uan
    -0.08
    уан
    -0.08
    ندڙ
    -0.08
     waitress
    -0.08
     chiropractor
    -0.07
     الخلي
    -0.07
    خاص
    -0.07
     naszych
    -0.07
    POSITIVE LOGITS
     lanz
    0.07
     hagu
    0.07
     constru
    0.07
    मैं
    0.07
     cómoda
    0.07
     Oder
    0.07
     Younger
    0.07
     intrusive
    0.07
     submitting
    0.06
    ̭
    0.06
    Activations Density 0.009%

    No Known Activations