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. 76079
    Prev
    Next
    INDEX
    Explanations

    proteins and neurodegenerative diseases

    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
    _ru
    -0.10
     negoti
    -0.09
     airfare
    -0.09
     deduct
    -0.09
     watered
    -0.09
    าณ
    -0.09
     deducted
    -0.08
     shutters
    -0.08
     budgeting
    -0.08
     deductible
    -0.08
    POSITIVE LOGITS
     amy
    0.15
     Alzheimer's
    0.11
     ubiquit
    0.10
     pathogenic
    0.10
     pathological
    0.10
     abnormal
    0.10
     Alzheimer
    0.10
     вред
    0.10
     toxicity
    0.09
     dementia
    0.09
    Activations Density 0.007%

    No Known Activations