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. 112064
    Prev
    Next
    INDEX
    Explanations

    machine learning, credit scoring

    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
     musicians
    -0.10
     bus
    -0.09
     misconception
    -0.09
    -svg
    -0.09
     Svg
    -0.09
     drummer
    -0.09
     guitarist
    -0.09
     MIDI
    -0.09
     Esperanto
    -0.09
    ardu
    -0.09
    POSITIVE LOGITS
     underwriting
    0.15
    贷款
    0.12
    审批
    0.11
     delin
    0.11
     जोखिम
    0.10
     dossiers
    0.10
    贷
    0.10
    审核
    0.10
    信用
    0.10
    风险
    0.10
    Activations Density 0.021%

    No Known Activations