© 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. 20378
    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
    ер
    -0.09
    ={
    -0.09
     различные
    -0.09
     everything
    -0.08
     everywhere
    -0.08
    ность
    -0.08
     разные
    -0.08
    ные
    -0.08
    গুলি
    -0.07
    everything
    -0.07
    POSITIVE LOGITS
    之一
    0.14
    usių
    0.11
    'яўляецца
    0.11
     genannten
    0.11
     angebot
    0.10
     האחר
    0.10
     הללו
    0.10
     является
    0.10
     પૈ
    0.10
     mwyaf
    0.10
    Activations Density 0.115%

    No Known Activations