© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 63948
    Prev
    Next
    INDEX
    Explanations

    Chinese legal and business texts

    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
     Tribal
    -0.10
     Sund
    -0.09
     Mitchell
    -0.09
     funky
    -0.08
    compr
    -0.08
     Marcus
    -0.08
     राज्य
    -0.08
     Likewise
    -0.08
     Mercury
    -0.08
     Chandler
    -0.08
    POSITIVE LOGITS
    ，
    0.16
    或者
    0.16
    和
    0.16
    并
    0.15
    ，不
    0.15
    或
    0.15
    进
    0.14
    相
    0.14
    丨
    0.14
    到
    0.14
    Activations Density 2.923%

    No Known Activations