© 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. 3-RESID-POST-AA
    11. 13474
    Prev
    Next
    INDEX
    Explanations

    whitening

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clocks
    -0.08
     Ej
    -0.07
    uire
    -0.07
    원의
    -0.07
     brakes
    -0.07
     SID
    -0.07
    ೂಕ
    -0.07
    Phy
    -0.07
    geko
    -0.07
     khỏe
    -0.07
    POSITIVE LOGITS
     unilateral
    0.08
    辦
    0.07
     DEV
    0.07
     Lang
    0.07
     lang
    0.07
     Aruba
    0.07
     bil
    0.07
     termen
    0.07
    -dev
    0.07
     junt
    0.07
    Activations Density 0.001%

    No Known Activations