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. 12942
    Prev
    Next
    INDEX
    Explanations

    numbers and math

    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
     securing
    -0.09
    .training
    -0.08
     מת
    -0.08
     bann
    -0.07
     המא
    -0.07
    _pas
    -0.07
     Centennial
    -0.07
     Banc
    -0.07
     Mc
    -0.07
    ্যান
    -0.07
    POSITIVE LOGITS
    ندا
    0.08
    പര
    0.08
    рел
    0.08
     очередь
    0.08
    \v
    0.08
    നിയ
    0.08
     помен
    0.08
     behaved
    0.07
     allocations
    0.07
     (§
    0.07
    Activations Density 0.067%

    No Known Activations