© 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. 21679
    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
    ers
    -0.09
    appropriate
    -0.08
    ervolle
    -0.08
    ationen
    -0.08
    eliz
    -0.08
    falls
    -0.08
    verte
    -0.07
    urations
    -0.07
    erl
    -0.07
     appropriate
    -0.07
    POSITIVE LOGITS
    ்ப்ப
    0.11
    ുടെ
    0.11
    ்த்த
    0.10
    قية
    0.10
    ்ந்து
    0.10
    ்த்து
    0.10
    ்ப்பு
    0.09
    ాండ్
    0.09
    առում
    0.09
    قاء
    0.09
    Activations Density 0.000%

    No Known Activations