© 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. 113542
    Prev
    Next
    INDEX
    Explanations

    kindness

    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
    poq
    -0.07
    /common
    -0.07
    poč
    -0.07
    式
    -0.06
     (?)
    -0.06
    ප්
    -0.06
    QC
    -0.06
    postas
    -0.06
    -0.06
    uration
    -0.06
    POSITIVE LOGITS
    .eg
    0.08
     unimaginable
    0.08
     انته
    0.08
    utations
    0.08
     ontem
    0.07
    Bee
    0.07
     outlaw
    0.07
     رجل
    0.07
     prieš
    0.07
     Elevator
    0.07
    Activations Density 0.010%
    No Known Activations