© 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. 54692
    Prev
    Next
    INDEX
    Explanations

    Non-English/code

    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
    습
    -0.09
    oren
    -0.09
    (Rem
    -0.08
     authenticate
    -0.08
    ಸ್ಕ
    -0.08
    lekt
    -0.08
    верх
    -0.08
    ಹೊ
    -0.08
     bevo
    -0.08
    ক্ষে
    -0.08
    POSITIVE LOGITS
     petals
    0.12
     blooming
    0.11
    艳
    0.10
     bloss
    0.10
     아름
    0.10
     blooms
    0.10
     blossoms
    0.09
     bloom
    0.09
     色
    0.09
     રંગ
    0.09
    Activations Density 0.006%

    No Known Activations