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. 49282
    Prev
    Next
    INDEX
    Explanations

    calculating numbers

    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
    %d
    -0.08
     pauta
    -0.08
     cak
    -0.08
    、电
    -0.08
     talent
    -0.07
     Alexand
    -0.07
    、この
    -0.07
     papa
    -0.07
    너지
    -0.07
    yac
    -0.07
    POSITIVE LOGITS
     dollars
    0.14
    美元
    0.13
    人民币
    0.13
    金额
    0.13
     financially
    0.13
     টাকা
    0.12
    USD
    0.12
     monetary
    0.12
     USD
    0.11
    เงิน
    0.11
    Activations Density 0.129%

    No Known Activations