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. 43822
    Prev
    Next
    INDEX
    Explanations

    looking

    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
     MAV
    -0.08
     conversar
    -0.08
     बताया
    -0.08
     jednoduch
    -0.07
     historian
    -0.07
    িমাণ
    -0.07
     parlant
    -0.07
     précis
    -0.07
     merit
    -0.07
    -0.07
    POSITIVE LOGITS
     слишком
    0.17
     liian
    0.16
     overly
    0.15
     excessively
    0.15
     too
    0.15
     undue
    0.14
     demasiado
    0.14
     unintended
    0.14
    too
    0.14
     incorrectly
    0.14
    Activations Density 0.162%

    No Known Activations