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. 111890
    Prev
    Next
    INDEX
    Explanations

    advice

    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
     demasi
    -0.09
    jpg
    -0.08
     Courtney
    -0.07
    jest
    -0.07
     بالد
    -0.07
     yy
    -0.07
     Nicolas
    -0.07
      ↵    ↵
    -0.07
    جون
    -0.07
    ddd
    -0.07
    POSITIVE LOGITS
     ideally
    0.11
     Ideally
    0.10
     preferably
    0.10
     olema
    0.09
     shouldn't
    0.09
    зывать
    0.08
    具
    0.08
     উচিত
    0.08
     tivesse
    0.08
     legyen
    0.08
    Activations Density 0.159%

    No Known Activations