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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 65829
    Prev
    Next
    INDEX
    Explanations

    portions

    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
    -producing
    -0.09
    cstdio
    -0.09
     produire
    -0.08
     생성
    -0.08
    yield
    -0.08
     Produce
    -0.08
     آدم
    -0.08
    izr
    -0.07
     produce
    -0.07
    cand
    -0.07
    POSITIVE LOGITS
    收费
    0.12
    料金
    0.12
     billed
    0.10
    费用
    0.10
     शुल्क
    0.10
     rounding
    0.10
     tariff
    0.09
     মিনিট
    0.09
    须
    0.09
    最长
    0.09
    Activations Density 0.020%

    No Known Activations