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. 58526
    Prev
    Next
    INDEX
    Explanations

    salary and payment

    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
    nog
    -0.08
    -invasive
    -0.08
    naa
    -0.07
     Pure
    -0.07
    'use
    -0.07
    pure
    -0.07
     gesloten
    -0.07
    违规
    -0.07
     Jud
    -0.07
    {}.
    -0.07
    POSITIVE LOGITS
     зарп
    0.15
     incomes
    0.14
    工资
    0.14
     salaries
    0.14
     salary
    0.13
     Einkommen
    0.13
    .salary
    0.13
    給与
    0.13
    salary
    0.13
     paycheck
    0.13
    Activations Density 0.035%

    No Known Activations