© 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. 19926
    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
     llor
    -0.08
    .dirname
    -0.08
     Mirage
    -0.07
    lero
    -0.07
     Mississippi
    -0.07
    >Select
    -0.07
     Brock
    -0.07
    .inverse
    -0.07
     experiências
    -0.07
     LESS
    -0.07
    POSITIVE LOGITS
     полноцен
    0.11
    full
    0.10
     full
    0.10
    ��
    0.09
     >=
    0.09
    ולות
    0.09
    Nth
    0.09
     nth
    0.09
    _FULL
    0.09
    Full
    0.09
    Activations Density 0.057%

    No Known Activations