© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 99753
    Prev
    Next
    INDEX
    Explanations

    death or ending

    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
     tension
    -0.08
     bursts
    -0.08
    ойчив
    -0.08
     bütün
    -0.08
     slick
    -0.07
     radius
    -0.07
     saturated
    -0.07
    _timeout
    -0.07
     tensión
    -0.07
     increments
    -0.07
    POSITIVE LOGITS
    -wife
    0.09
     obituary
    0.09
     deceased
    0.09
    idagi
    0.08
    Sibling
    0.08
     acquaintances
    0.08
     funeral
    0.08
     predecessors
    0.08
     olnud
    0.08
     relatives
    0.08
    Activations Density 0.003%

    No Known Activations