© 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. 23-RESID-POST-AA
    11. 49607
    Prev
    Next
    INDEX
    Explanations

    say "59"

    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
    ่วย
    -0.08
    Wel
    -0.08
    Arch
    -0.08
    Liber
    -0.08
    .output
    -0.07
     absorbing
    -0.07
    Shutdown
    -0.07
     Flush
    -0.07
    .plan
    -0.07
    規
    -0.07
    POSITIVE LOGITS
     cyfl
    0.08
     sý
    0.07
     kpọ
    0.07
     feet
    0.07
    〒
    0.07
     underscore
    0.07
     termo
    0.07
     express
    0.07
     EXPRESS
    0.07
     kece
    0.07
    Activations Density 0.001%

    No Known Activations