© 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. 30156
    Prev
    Next
    INDEX
    Explanations

    question problem

    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
    ません
    -0.08
     integrates
    -0.08
    imler
    -0.07
    enge
    -0.07
    olie
    -0.07
    umming
    -0.07
    ())))↵
    -0.07
     Env
    -0.07
     wouldn
    -0.07
     choses
    -0.07
    POSITIVE LOGITS
     সম্পর্ক
    0.08
     bookshelf
    0.08
     bastard
    0.08
     bằng
    0.08
     הזה
    0.08
     المتعلقة
    0.08
     związ
    0.08
     הזאת
    0.07
    יקס
    0.07
    OR
    0.07
    Activations Density 0.021%

    No Known Activations