© 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 EvalsExportsinterp-engineNEWAPI 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. 70440
    Prev
    Next
    INDEX
    Explanations

    Numbers near 1000

    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
     cit
    -0.08
    eles
    -0.08
    kaa
    -0.08
     Creat
    -0.07
     Leaders
    -0.07
     Sims
    -0.07
     Odd
    -0.07
    .seed
    -0.07
     Leopold
    -0.07
    .fre
    -0.07
    POSITIVE LOGITS
    tri
    0.08
     brick
    0.08
     bikini
    0.07
    IS
    0.07
    0.07
    quiv
    0.07
    triangle
    0.07
    错误
    0.07
     sein
    0.07
    梯
    0.07
    Activations Density 0.104%
    No Known Activations