© 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. 25918
    Prev
    Next
    INDEX
    Explanations

    process scheduling

    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
     oils
    -0.09
     selfie
    -0.08
    іпті
    -0.08
    (ierr
    -0.08
     peau
    -0.08
    üp
    -0.08
    装备
    -0.08
    raînement
    -0.08
    associate
    -0.08
     hashtags
    -0.08
    POSITIVE LOGITS
     fairness
    0.12
    Shortest
    0.11
     Priority
    0.10
    公平
    0.10
    _PRIORITY
    0.10
    Priority
    0.10
    _priority
    0.10
    .priority
    0.10
     priority
    0.09
     FIFO
    0.09
    Activations Density 0.005%

    No Known Activations