© 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. 29230
    Prev
    Next
    INDEX
    Explanations

    acid-free

    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
    Division
    -0.10
     division
    -0.09
    ่านั้น
    -0.09
     Division
    -0.09
    Barang
    -0.08
     seamless
    -0.08
     Ministar
    -0.08
     ipak
    -0.08
     ยู
    -0.08
     chipped
    -0.08
    POSITIVE LOGITS
     infancy
    0.08
     purge
    0.08
     automatis
    0.08
     stems
    0.08
     beware
    0.08
    0.07
     stemming
    0.07
    stemming
    0.07
    Late
    0.07
    hren
    0.07
    Activations Density 0.006%
    No Known Activations