© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 21421
    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
     дополнительные
    -0.08
     they
    -0.08
     They
    -0.08
     Proto
    -0.08
    They
    -0.08
     Happy
    -0.07
    yaml
    -0.07
    10
    -0.07
     +#+
    -0.07
     તેઓ
    -0.07
    POSITIVE LOGITS
    -Ф
    0.14
    /"
    0.13
    /[
    0.13
    /K
    0.12
    /"↵
    0.12
    /R
    0.12
    -К
    0.12
    /",
    0.12
    /",↵
    0.12
    /#{
    0.12
    Activations Density 0.002%

    No Known Activations