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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 88079
    Prev
    Next
    INDEX
    Explanations

    agreement

    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
    omia
    -0.08
     immigration
    -0.08
     prepara
    -0.07
     Immigration
    -0.07
    罩
    -0.07
     usia
    -0.07
    ilin
    -0.07
    '}>↵
    -0.07
     enormes
    -0.07
    واس
    -0.07
    POSITIVE LOGITS
    观点
    0.11
     주장
    0.10
     বক্তব্য
    0.10
     ಹೇಳ
    0.10
     disagree
    0.10
     disag
    0.09
     ಹೇಳಿದ್ದಾರೆ
    0.09
     പറഞ്ഞ
    0.08
     의견
    0.08
     disagreement
    0.08
    Activations Density 0.046%

    No Known Activations