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. 23-RESID-POST-AA
    6. 98498
    Prev
    Next
    INDEX
    Explanations

    اذ

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arfik
    -0.08
    ствуют
    -0.08
    шілік
    -0.08
     Cambodia
    -0.08
    entas
    -0.08
    imamente
    -0.08
    irem
    -0.08
     leverage
    -0.07
    nahme
    -0.07
    ada
    -0.07
    POSITIVE LOGITS
    ج
    0.13
    جين
    0.10
    جات
    0.09
    जा
    0.09
    جے
    0.09
    (shape
    0.08
    janje
    0.08
    jis
    0.08
    جہ
    0.08
    ਜ
    0.08
    Activations Density 0.001%

    No Known Activations