© 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. 1084
    Prev
    Next
    INDEX
    Explanations

    ly

    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
     pharmaceutical
    -0.09
     substances
    -0.08
     Furn
    -0.08
     pharmaceuticals
    -0.08
     fratern
    -0.08
    ertil
    -0.08
     fluoride
    -0.08
    ocr
    -0.08
     furnished
    -0.08
    戒
    -0.07
    POSITIVE LOGITS
     footage
    0.11
     panoramic
    0.10
    Smooth
    0.10
     घूम
    0.10
    Tween
    0.09
    smooth
    0.09
     smooth
    0.09
     Smooth
    0.09
     Slowly
    0.09
     langsam
    0.09
    Activations Density 0.007%

    No Known Activations