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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 43421
    Prev
    Next
    INDEX
    Explanations

    Mathematical expression manipulation

    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
    救世
    -0.09
    设计
    -0.08
    百分
    -0.08
     বাঁ
    -0.08
     अवस्था
    -0.08
    预计
    -0.08
     وحدة
    -0.08
     اختبار
    -0.08
    ولد
    -0.08
     кел
    -0.08
    POSITIVE LOGITS
    Subtract
    0.10
     Exclusive
    0.09
    excluding
    0.09
     Comparing
    0.09
     excludes
    0.09
     목록
    0.08
     excluding
    0.08
    Forex
    0.08
    Compar
    0.08
    indexed
    0.08
    Activations Density 0.020%

    No Known Activations