© 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. 129373
    Prev
    Next
    INDEX
    Explanations

    you

    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
    '''↵
    -0.08
    ，好
    -0.07
     好
    -0.07
     必
    -0.07
     cohes
    -0.07
    coll
    -0.07
     法
    -0.07
     可以
    -0.07
     �
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     quý
    0.10
     감사
    0.10
     답
    0.09
     beant
    0.08
     warmth
    0.08
     toqu
    0.08
    0.08
    녕하세요
    0.08
    uria
    0.08
     chút
    0.08
    Activations Density 0.013%
    No Known Activations