© 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. 99176
    Prev
    Next
    INDEX
    Explanations

    once

    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
    工业
    -0.08
    šla
    -0.08
     Shenzhen
    -0.08
    当前位置
    -0.08
    óvil
    -0.08
     sağlık
    -0.08
     zdrow
    -0.07
     ആരോഗ
    -0.07
     بالر
    -0.07
     муль
    -0.07
    POSITIVE LOGITS
     repertoire
    0.10
     Weapon
    0.10
     atrocities
    0.09
    Repeat
    0.08
     कौ
    0.08
     repert
    0.08
     offense
    0.08
     Repeat
    0.08
     Skill
    0.08
    repeat
    0.08
    Activations Density 0.002%

    No Known Activations