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. 112213
    Prev
    Next
    INDEX
    Explanations

    we

    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
     Micros
    -0.08
    Duck
    -0.08
    Sweep
    -0.08
     పొ
    -0.08
    /event
    -0.08
    omial
    -0.08
    /per
    -0.08
     Lottery
    -0.08
    事实上
    -0.08
     Shack
    -0.08
    POSITIVE LOGITS
     analyze
    0.08
    遵
    0.08
     should
    0.08
     unravel
    0.08
    نب
    0.08
     assume
    0.08
     elaborate
    0.07
    рем
    0.07
     Vas
    0.07
     rigorous
    0.07
    Activations Density 0.088%

    No Known Activations