Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2109
    Prev
    Next
    INDEX
    Explanations

    锁

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     خون
    -0.07
     리뷰
    -0.07
    有没有
    -0.07
     sofre
    -0.07
     koup
    -0.07
     SEX
    -0.07
    ਾਇਆ
    -0.07
     tally
    -0.07
    bab
    -0.07
     peaches
    -0.07
    POSITIVE LOGITS
     CPT
    0.08
    цией
    0.08
     Helic
    0.08
     tray
    0.08
    Howard
    0.08
    বর
    0.07
     worker
    0.07
    ün
    0.07
    டிய
    0.07
    rol
    0.07
    Activations Density 0.002%

    No Known Activations