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. 88142
    Prev
    Next
    INDEX
    Explanations

    noise

    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
     irresponsible
    -0.08
     boilers
    -0.08
    ය
    -0.08
     tantr
    -0.08
     junk
    -0.08
     zit
    -0.08
     punished
    -0.08
    lə
    -0.08
     sails
    -0.08
    帰
    -0.08
    POSITIVE LOGITS
     vividly
    0.09
    Comma
    0.08
     conducive
    0.08
    柔
    0.08
    Optimal
    0.08
     soothing
    0.08
    (".",
    0.07
    Option
    0.07
     Mild
    0.07
    ở
    0.07
    Activations Density 0.005%

    No Known Activations