© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 21207
    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
     แมน
    -0.10
     şimdi
    -0.10
    ันธ์
    -0.10
     maann
    -0.10
     быз
    -0.10
     beteil
    -0.09
     շրջան
    -0.09
     eqqu
    -0.09
     akorn
    -0.09
     ดาว
    -0.09
    POSITIVE LOGITS
    /
    0.11
    x
    0.10
    ×
    0.10
    Hz
    0.09
    such
    0.09
    %
    0.09
    \(
    0.09
    /or
    0.09
    
    0.09
    %的
    0.09
    Activations Density 0.011%

    No Known Activations