© 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. 24721
    Prev
    Next
    INDEX
    Explanations

    accounting calculations

    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
     geek
    -0.09
     Esperanto
    -0.09
     快乐
    -0.09
     Scientists
    -0.09
    科学
    -0.09
     GLFW
    -0.08
    maze
    -0.08
     বিজ্ঞান
    -0.08
    快乐
    -0.08
     весел
    -0.08
    POSITIVE LOGITS
     sebesar
    0.11
     fiscal
    0.11
     Payroll
    0.11
     payroll
    0.11
    金额
    0.10
     Fiscal
    0.10
     pror
    0.10
    Fiscal
    0.10
     revenues
    0.10
     taxable
    0.10
    Activations Density 0.016%

    No Known Activations