© 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. 19-RESID-POST-AA
    11. 20898
    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
     accordingly
    -0.10
     daarvoor
    -0.09
    othing
    -0.08
     thereof
    -0.08
     därför
    -0.08
    ?!?!
    -0.08
    pdev
    -0.08
     всю
    -0.08
     (
    -0.08
    <-
    -0.08
    POSITIVE LOGITS
    Anyway
    0.10
     ಅಥವಾ
    0.09
     atau
    0.09
     ಮತ್ತು
    0.09
     আৰু
    0.08
     või
    0.08
     կամ
    0.08
     কিংবা
    0.08
     hoặc
    0.08
     skute
    0.08
    Activations Density 0.142%

    No Known Activations