© 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. 18331
    Prev
    Next
    INDEX
    Explanations

    scientific publications

    np_max-act-logits · gemini-2.0-flash
    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
     I'
    -0.08
    レビ
    -0.08
    ummy
    -0.07
    mare
    -0.07
     apporter
    -0.07
     સિ
    -0.07
     AS
    -0.07
    -than
    -0.07
     TAKE
    -0.07
     બેઠક
    -0.07
    POSITIVE LOGITS
    357
    0.10
    954
    0.09
    246
    0.09
    146
    0.09
    874
    0.09
    237
    0.09
    647
    0.08
    138
    0.08
    279
    0.08
    959
    0.08
    Activations Density 0.001%

    No Known Activations