© 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. 19-RESID-POST-AA
    11. 18537
    Prev
    Next
    INDEX
    Explanations

    Chemistry

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "
    -0.14
    「
    -0.13
    �
    -0.12
    202
    -0.11
    �
    -0.11
    《
    -0.11
    —
    -0.10
     perhaps
    -0.10
    �
    -0.10
     '
    -0.10
    POSITIVE LOGITS
     rf
    0.11
     값을
    0.09
     rb
    0.09
     գում
    0.09
     
    0.09
     rms
    0.09
     ....↵
    0.09
     vmax
    0.09
     unary
    0.09
    二维
    0.09
    Activations Density 0.061%

    No Known Activations