© 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. 8147
    Prev
    Next
    INDEX
    Explanations

    answer

    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
    ainless
    -0.08
    itores
    -0.08
    ไร
    -0.08
    Bots
    -0.07
     CNS
    -0.07
     kyl
    -0.07
    .How
    -0.07
    akhulu
    -0.07
    .opt
    -0.07
    Drv
    -0.07
    POSITIVE LOGITS
     berupa
    0.09
     Textile
    0.08
     produkto
    0.08
     pumping
    0.08
     pumped
    0.08
    商品の
    0.08
    列
    0.08
     showcasing
    0.08
    展示
    0.07
    лал
    0.07
    Activations Density 0.031%

    No Known Activations