© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 45445
    Prev
    Next
    INDEX
    Explanations

    the

    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
     treated
    -0.08
    स्त
    -0.08
    fonts
    -0.08
    agrad
    -0.08
    Treat
    -0.08
    (vertices
    -0.08
    Faces
    -0.08
    Typeface
    -0.08
    JSONArray
    -0.08
    thouse
    -0.08
    POSITIVE LOGITS
     consumption
    0.08
     USB
    0.08
     Therm
    0.08
     watt
    0.08
     watchdog
    0.08
     Scholar
    0.08
     voltage
    0.08
     voeding
    0.08
     intake
    0.08
     reclam
    0.08
    Activations Density 0.006%

    No Known Activations