© 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. 22307
    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
    umise
    -0.09
    anyisa
    -0.09
    .Nullable
    -0.08
    .Threading
    -0.08
     perkara
    -0.08
     anthu
    -0.08
    adastro
    -0.08
    anyang
    -0.08
     jalma
    -0.08
    اضة
    -0.08
    POSITIVE LOGITS
     is
    0.08
    maybe
    0.08
    '.↵
    0.08
    *
    0.08
    ा
    0.08
     maybe
    0.08
    ಿ
    0.07
    ISE
    0.07
    ા
    0.07
     closely
    0.07
    Activations Density 0.051%

    No Known Activations