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. 75895
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     ').
    -0.07
     disclaim
    -0.07
     نقاط
    -0.07
     smoking
    -0.07
    威
    -0.07
     threats
    -0.07
    нова
    -0.07
     zien
    -0.07
     강조
    -0.07
    abka
    -0.07
    POSITIVE LOGITS
     gated
    0.09
     excessive
    0.09
    费用
    0.08
     encaps
    0.08
     avo
    0.08
     biaya
    0.08
    Writer
    0.08
     NSK
    0.08
     isbn
    0.08
    overflow
    0.08
    Activations Density 0.003%

    No Known Activations