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. 61215
    Prev
    Next
    INDEX
    Explanations

    response

    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
     apost
    -0.09
    輸
    -0.08
     chr
    -0.08
     intento
    -0.08
    chr
    -0.08
     hanggang
    -0.08
     amino
    -0.08
     huevos
    -0.07
     croche
    -0.07
     gamit
    -0.07
    POSITIVE LOGITS
    智能
    0.09
     स्मार्ट
    0.09
    .unsubscribe
    0.09
     Consumers
    0.09
     스마트
    0.09
     inteligentes
    0.09
     smart
    0.09
     smarter
    0.08
    Smart
    0.08
    .Consumer
    0.08
    Activations Density 0.006%

    No Known Activations