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. 53047
    Prev
    Next
    INDEX
    Explanations

    totals

    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
     Scientists
    -0.10
     scientists
    -0.10
    Scientists
    -0.09
     mutants
    -0.08
    arab
    -0.08
    _dirs
    -0.08
     Lives
    -0.08
     acoust
    -0.08
    mouseenter
    -0.08
    gene
    -0.08
    POSITIVE LOGITS
    付款
    0.15
    贷款
    0.14
    费用
    0.14
     payments
    0.14
    (payment
    0.14
     payment
    0.14
     pembayaran
    0.14
     शुल्क
    0.13
     भुगतान
    0.13
     paiement
    0.13
    Activations Density 0.017%

    No Known Activations