© 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. 69892
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings

    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
     حك
    -0.08
     Err
    -0.08
     والاج
    -0.08
    Say
    -0.07
     multifunction
    -0.07
    Mental
    -0.07
    /right
    -0.07
     الحكم
    -0.07
     وين
    -0.07
    Preview
    -0.07
    POSITIVE LOGITS
     дли
    0.09
    长度
    0.09
    .split
    0.08
     ನಡೆಯ
    0.08
     comprimento
    0.08
     Länge
    0.08
     minlength
    0.08
     seid
    0.08
    .length
    0.08
     formaat
    0.08
    Activations Density 0.004%

    No Known Activations