© 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. 1067
    Prev
    Next
    INDEX
    Explanations

    World

    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
    念
    -0.09
     pouca
    -0.08
    Networking
    -0.08
    Bytes
    -0.08
    性色
    -0.08
    不足
    -0.08
     ব্য
    -0.08
    在線
    -0.08
    bytes
    -0.07
     inse
    -0.07
    POSITIVE LOGITS
     виз
    0.08
     Hr
    0.08
     woh
    0.08
     Abr
    0.07
     eam
    0.07
     spur
    0.07
     striking
    0.07
     चल
    0.07
     dele
    0.07
       
    0.07
    Activations Density 0.000%

    No Known Activations