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. 11-RESID-POST-AA
    6. 53952
    Prev
    Next
    INDEX
    Explanations

    message

    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
    知ら
    -0.07
    万人
    -0.07
    _cpu
    -0.07
     knew
    -0.07
     świata
    -0.07
     오
    -0.07
     cidade
    -0.07
    _OBJ
    -0.07
     deut
    -0.07
    ുവര
    -0.07
    POSITIVE LOGITS
     vetted
    0.09
    cloth
    0.09
     Juríd
    0.09
     अनुस
    0.08
    টির
    0.08
    ंड
    0.08
     নিয়ে
    0.08
     ivo
    0.08
     ऐ
    0.08
     جاه
    0.08
    Activations Density 0.001%

    No Known Activations