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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98149
    Prev
    Next
    INDEX
    Explanations

    taxes and revenue

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _tax
    -0.12
     Tax
    -0.12
     taxonomy
    -0.12
     tax
    -0.12
    Tax
    -0.12
    taxonomy
    -0.10
    -tax
    -0.10
    .tax
    -0.10
    税
    -0.10
    tax
    -0.10
    POSITIVE LOGITS
     Value
    0.16
     Einkommen
    0.15
     income
    0.15
     Consumption
    0.15
     corporation
    0.15
    Value
    0.14
     consumption
    0.14
     Income
    0.14
     corporate
    0.14
    .Value
    0.13
    Activations Density 0.021%

    No Known Activations