© 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. 63800
    Prev
    Next
    INDEX
    Explanations

    business failures

    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
    Verified
    -0.09
    verified
    -0.08
     verified
    -0.08
    oglob
    -0.08
     три
    -0.07
    <Link
    -0.07
     assures
    -0.07
    Bracket
    -0.07
    }_${
    -0.07
     trening
    -0.07
    POSITIVE LOGITS
    lack
    0.11
     слишком
    0.10
     overly
    0.10
     Lack
    0.10
     terlalu
    0.10
     cripple
    0.10
     downfall
    0.10
     Poor
    0.09
     schlechter
    0.09
     lacked
    0.09
    Activations Density 0.089%

    No Known Activations