© 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. 11-RESID-POST-AA
    11. 70222
    Prev
    Next
    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ho
    -0.08
     troubleshoot
    -0.08
    .repaint
    -0.08
    arak
    -0.08
    HBox
    -0.08
    ash
    -0.08
     troubleshooting
    -0.07
     호
    -0.07
    kom
    -0.07
    tho
    -0.07
    POSITIVE LOGITS
     occurrences
    0.09
     uniform
    0.08
    男女
    0.08
     occurrence
    0.08
     bingo
    0.08
     periods
    0.08
     જીત
    0.08
     Bingo
    0.07
     participation
    0.07
     desej
    0.07
    Activations Density 0.018%

    No Known Activations