© 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. 26555
    Prev
    Next
    INDEX
    Explanations

    Processing tasks and departments

    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
     rugby
    -0.07
     resurgence
    -0.07
    &oacute
    -0.07
     church
    -0.07
     cricket
    -0.07
    вад
    -0.07
     kork
    -0.07
    😊
    -0.07
     cherished
    -0.07
     cursed
    -0.07
    POSITIVE LOGITS
     processing
    0.12
    加工
    0.12
     стадии
    0.12
     обработки
    0.12
     downstream
    0.11
    阶段
    0.11
     processamento
    0.11
     procesamiento
    0.11
     مرحلة
    0.10
     Verarbeitung
    0.10
    Activations Density 0.030%

    No Known Activations