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. 43245
    Prev
    Next
    INDEX
    Explanations

    financial returns

    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
     banned
    -0.09
     صح
    -0.08
    禁止
    -0.08
    男子
    -0.08
    Forbidden
    -0.08
    Nowadays
    -0.08
    隊
    -0.08
     جماعت
    -0.08
     picky
    -0.08
    икой
    -0.08
    POSITIVE LOGITS
     profitability
    0.12
    profits
    0.11
     profitable
    0.10
     Investment
    0.10
     financing
    0.10
    .loan
    0.10
     fiscal
    0.10
    利润
    0.10
     ROI
    0.10
     инвест
    0.10
    Activations Density 0.013%

    No Known Activations