© 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. 95054
    Prev
    Next
    INDEX
    Explanations

    lesson

    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
     enthusiast
    -0.08
     grunt
    -0.08
     headset
    -0.08
     entusias
    -0.07
     porn
    -0.07
     pesta
    -0.07
    clusive
    -0.07
     assault
    -0.07
    PVC
    -0.07
    rut
    -0.07
    POSITIVE LOGITS
     lessons
    0.21
     lesson
    0.20
     Lessons
    0.19
    Lessons
    0.18
    Lesson
    0.17
     Lesson
    0.17
     урок
    0.16
    lesson
    0.15
     teachings
    0.13
     آموز
    0.13
    Activations Density 0.078%

    No Known Activations