Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12158
    Prev
    Next
    INDEX
    Explanations

    exponents and math theorems

    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
     Κ
    -0.08
     sc
    -0.08
     stale
    -0.07
    Able
    -0.07
     cellulose
    -0.07
    ώ
    -0.07
    Mist
    -0.07
    78
    -0.07
    Wait
    -0.07
    Κ
    -0.07
    POSITIVE LOGITS
    feest
    0.08
     математ
    0.08
     mathematical
    0.08
     holl
    0.08
     analogy
    0.08
    etris
    0.07
    oree
    0.07
     sommer
    0.07
     تحفظ
    0.07
    ල්ල
    0.07
    Activations Density 0.027%

    No Known Activations