© 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. 245
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Descripción
    -0.08
     descrição
    -0.08
    Descrição
    -0.07
    Codes
    -0.07
    颜色
    -0.07
     procur
    -0.07
     muv
    -0.07
    方便
    -0.07
    ppt
    -0.07
     steaming
    -0.07
    POSITIVE LOGITS
     rhetoric
    0.10
     convain
    0.10
     provocative
    0.10
     criticizing
    0.10
     skepticism
    0.10
     രാഷ്ട്രീയ
    0.10
     outspoken
    0.09
     accusing
    0.09
    观点
    0.09
     überzeug
    0.09
    Activations Density 0.290%

    No Known Activations