© 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. 11-RESID-POST-AA
    11. 68875
    Prev
    Next
    INDEX
    Explanations

    Lab safety instructions

    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
     disasters
    -0.08
     Carpet
    -0.08
     desastre
    -0.08
     Disaster
    -0.08
     aporte
    -0.08
     compressor
    -0.08
     Fall
    -0.08
    Fund
    -0.08
    omap
    -0.08
    fp
    -0.07
    POSITIVE LOGITS
    ande
    0.08
     taf
    0.08
    -st
    0.08
     venen
    0.08
    Pada
    0.07
    priet
    0.07
    Electronic
    0.07
     aura
    0.07
    [L
    0.07
    -treated
    0.07
    Activations Density 0.004%

    No Known Activations