© 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. 18672
    Prev
    Next
    INDEX
    Explanations

    public

    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
    inei
    -0.09
    ivatives
    -0.09
     onderscheid
    -0.08
    *np
    -0.08
    ivée
    -0.08
    enciamento
    -0.08
    owitz
    -0.08
    ardy
    -0.08
    "},{"
    -0.07
     statistical
    -0.07
    POSITIVE LOGITS
     {↵↵
    0.11
     {
↵
↵
    0.10
     final
    0.10
     класса
    0.09
     {↵↵↵
    0.09
    final
    0.09
    레
    0.09
    {
↵
↵
    0.09
     class
    0.09
    	final
    0.08
    Activations Density 0.000%

    No Known Activations