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. 88291
    Prev
    Next
    INDEX
    Explanations

    English text and code

    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
    OOD
    -0.10
     küçük
    -0.08
     ork
    -0.08
     Convenient
    -0.08
    alisme
    -0.08
     kleine
    -0.08
     मुदा
    -0.08
    “小
    -0.08
     रोल
    -0.07
     conveniente
    -0.07
    POSITIVE LOGITS
     পরীক্ষ
    0.07
     newsletter
    0.07
     تحلیل
    0.07
     പരിശോധന
    0.07
     Interpreter
    0.07
     profiling
    0.07
     Mohamed
    0.07
    .test
    0.07
     Guadalupe
    0.07
     평가
    0.07
    Activations Density 0.002%

    No Known Activations