© 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. 18742
    Prev
    Next
    INDEX
    Explanations

    cost

    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
     Reduced
    -0.09
     Less
    -0.08
     Updated
    -0.08
     Performance
    -0.08
     Offered
    -0.08
     USP
    -0.07
     Amerikaanse
    -0.07
     Selected
    -0.07
     అదే
    -0.07
     Edited
    -0.07
    POSITIVE LOGITS
     implications
    0.15
     burden
    0.15
     burdens
    0.14
     incurred
    0.14
     implication
    0.12
    ly
    0.12
     associated
    0.12
     impli
    0.12
     부담
    0.11
     implica
    0.11
    Activations Density 0.017%

    No Known Activations