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. 30131
    Prev
    Next
    INDEX
    Explanations

    math calculations

    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
     computation
    -0.09
    .compute
    -0.09
     calculating
    -0.09
     Comput
    -0.08
    _PAY
    -0.08
    .calculate
    -0.08
     стоимости
    -0.08
     Calculation
    -0.08
     calculations
    -0.08
     calcula
    -0.08
    POSITIVE LOGITS
     reorder
    0.12
    排列
    0.12
     ordering
    0.12
     reordered
    0.11
     סדר
    0.11
    排序
    0.11
     क्रम
    0.10
    ordering
    0.10
     arrangement
    0.10
    Ordering
    0.10
    Activations Density 0.024%

    No Known Activations