© 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. 23-RESID-POST-AA
    11. 50748
    Prev
    Next
    INDEX
    Explanations

    get

    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
    *
↵
    -0.09
    objs
    -0.08
    *)((
    -0.08
    typename
    -0.08
    every
    -0.08
     Root
    -0.08
     ""
↵
    -0.08
    ()))↵↵
    -0.08
    objects
    -0.08
    startswith
    -0.07
    POSITIVE LOGITS
    ;
    0.18
     {
    0.14
    {return
    0.13
    {
    0.12
    ;padding
    0.11
     =>
    0.11
    ;border
    0.11
     {↵
    0.10
    ;">↵
    0.10
    .set
    0.09
    Activations Density 0.001%

    No Known Activations