© 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. 7-RESID-POST-AA
    11. 1364
    Prev
    Next
    INDEX
    Explanations

    Array

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ギ
    -0.08
    erge
    -0.08
     ギ
    -0.08
    वर्क
    -0.08
     мәз
    -0.08
     versi
    -0.08
     //
↵
    -0.08
     бед
    -0.07
     /**
↵
    -0.07
    援
    -0.07
    POSITIVE LOGITS
    保存
    0.07
     관리
    0.07
     Produkt
    0.07
     misl
    0.07
    Straight
    0.07
     Virginia
    0.07
     Tus
    0.07
    .savefig
    0.07
     persec
    0.07
     ABC
    0.07
    Activations Density 0.000%

    No Known Activations