© 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. 47988
    Prev
    Next
    INDEX
    Explanations

    technology in education

    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
     buried
    -0.08
     taxi
    -0.08
     casinos
    -0.08
     weth
    -0.08
     sens
    -0.08
     insured
    -0.07
     bearish
    -0.07
     luxurious
    -0.07
     perfume
    -0.07
     الجنسية
    -0.07
    POSITIVE LOGITS
     enseignants
    0.16
    .teacher
    0.16
    教师
    0.16
     Moodle
    0.15
     педагог
    0.15
    教学
    0.15
    Teacher
    0.15
    Teachers
    0.15
     pedagog
    0.15
     classroom
    0.15
    Activations Density 0.054%

    No Known Activations