© 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. 22071
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ,email
    -0.08
     இரண்டு
    -0.08
     দুটি
    -0.08
     dalawang
    -0.08
    三个
    -0.08
     triple
    -0.08
    ,address
    -0.08
     రెండు
    -0.08
     രണ്ട്
    -0.08
    $email
    -0.08
    POSITIVE LOGITS
     predefined
    0.20
     常
    0.16
     commonly
    0.16
    常
    0.16
     основные
    0.15
     standard
    0.15
     common
    0.15
    /common
    0.15
    Common
    0.15
     comunes
    0.14
    Activations Density 0.105%

    No Known Activations