© 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. 45787
    Prev
    Next
    INDEX
    Explanations

    fabric

    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
    面积
    -0.10
    -0.08
    规模
    -0.08
     traslad
    -0.08
     Area
    -0.08
     ночью
    -0.07
     Tir
    -0.07
     क्षेत्र
    -0.07
    area
    -0.07
    _area
    -0.07
    POSITIVE LOGITS
     woven
    0.11
     fabric
    0.09
     Bestandteil
    0.09
     fabrics
    0.08
     tapestry
    0.08
     tissu
    0.08
     tecido
    0.08
     برخ
    0.08
     seemingly
    0.08
    kw
    0.08
    Activations Density 0.008%
    No Known Activations