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. 87982
    Prev
    Next
    INDEX
    Explanations

    ://

    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
     rond
    -0.08
     poud
    -0.07
    cription
    -0.07
     separately
    -0.07
    秘书
    -0.07
    asol
    -0.07
    -members
    -0.07
    beds
    -0.07
     powder
    -0.07
     rises
    -0.07
    POSITIVE LOGITS
     Insights
    0.09
    Insights
    0.08
    youtu
    0.08
    γή
    0.08
    _REFER
    0.08
     CLI
    0.08
    www
    0.08
    _LENGTH
    0.07
     Harry
    0.07
     चे
    0.07
    Activations Density 0.029%

    No Known Activations