© 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. 19-RESID-POST-AA
    11. 103173
    Prev
    Next
    INDEX
    Explanations

    tensor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ماه
    -0.08
     grew
    -0.08
    аха
    -0.08
    았다
    -0.08
    =-=-
    -0.08
    var
    -0.08
    vala
    -0.08
    Growing
    -0.07
    сих
    -0.07
     growing
    -0.07
    POSITIVE LOGITS
    產品
    0.10
     제품
    0.10
     ಉತ್ಪ
    0.09
     उत्पाद
    0.09
     Product
    0.09
    -product
    0.09
     ürün
    0.09
     products
    0.08
     product
    0.08
     المنتجات
    0.08
    Activations Density 0.001%

    No Known Activations