© 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. 23-RESID-POST-AA
    11. 6352
    Prev
    Next
    INDEX
    Explanations

    avi

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppers
    -0.09
    ensed
    -0.08
    static
    -0.07
    .Reader
    -0.07
    теп
    -0.07
     gradients
    -0.07
    pped
    -0.07
    .Det
    -0.07
    enses
    -0.07
    әз
    -0.07
    POSITIVE LOGITS
    ายใน
    0.08
     تص
    0.08
    ுல
    0.08
     Neil
    0.08
     Sitting
    0.08
    નિક
    0.08
    วจ
    0.07
     ACM
    0.07
     gol
    0.07
     Shui
    0.07
    Activations Density 0.000%

    No Known Activations