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. 53963
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs

    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
     Bitcoin
    -0.09
     suggesting
    -0.08
     bank
    -0.08
     BTC
    -0.08
     BIT
    -0.07
     suggests
    -0.07
     Lake
    -0.07
    Bitcoin
    -0.07
     Slovakia
    -0.07
     swiss
    -0.07
    POSITIVE LOGITS
    ণ্ট
    0.10
    երն
    0.08
    ურდ
    0.08
    ∙
    0.08
     მეო
    0.08
     선언
    0.08
     پې
    0.08
     léir
    0.08
     igles
    0.08
     אלע
    0.08
    Activations Density 0.167%

    No Known Activations