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. 53955
    Prev
    Next
    INDEX
    Explanations

    division problems

    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
    PIRED
    -0.09
     mitochondrial
    -0.08
     compose
    -0.07
    광
    -0.07
     Proms
    -0.07
     haunting
    -0.07
     expired
    -0.07
     Prius
    -0.07
     Sullivan
    -0.07
     Aerospace
    -0.07
    POSITIVE LOGITS
     evenly
    0.16
     توزيع
    0.14
     distribuir
    0.14
     equitable
    0.14
     distribute
    0.14
     uniform
    0.13
     distributing
    0.13
     distributes
    0.13
     распредел
    0.13
    均
    0.13
    Activations Density 0.048%

    No Known Activations