© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30070
    Prev
    Next
    INDEX
    Explanations

    income and taxes

    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
     branching
    -0.08
     Eternal
    -0.08
    !!↵↵
    -0.08
     please
    -0.08
     Bug
    -0.08
     פר
    -0.08
     liber
    -0.08
     ngah
    -0.07
     অধ্য
    -0.07
     খুল
    -0.07
    POSITIVE LOGITS
     incomes
    0.10
    income
    0.10
     ఆద
    0.10
    Income
    0.09
     rebates
    0.09
     socioeconomic
    0.09
     Einkommen
    0.09
     낮
    0.09
    Applicant
    0.09
     गरी
    0.09
    Activations Density 0.019%

    No Known Activations