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. 55902
    Prev
    Next
    INDEX
    Explanations

    chamomile

    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
    ाटन
    -0.08
     mínimos
    -0.08
    तीय
    -0.08
    낌
    -0.08
     년
    -0.08
     frac
    -0.08
    途中
    -0.08
    rawl
    -0.08
     विधान
    -0.07
    दी
    -0.07
    POSITIVE LOGITS
     incision
    0.09
     serenity
    0.09
     Arial
    0.08
     anxiety
    0.08
     soothing
    0.08
     শান্ত
    0.08
     whey
    0.08
     Earl
    0.07
     Doh
    0.07
     sedation
    0.07
    Activations Density 0.004%

    No Known Activations