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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 45300
    Prev
    Next
    INDEX
    Explanations

    Warehouse management systems

    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
     whirl
    -0.09
     perigo
    -0.09
    cyclerview
    -0.08
     vias
    -0.08
     misterio
    -0.08
     eterna
    -0.08
    )){
    -0.08
     dreamy
    -0.08
    bev
    -0.08
    uesday
    -0.08
    POSITIVE LOGITS
     пав
    0.08
    采
    0.08
     SAP
    0.08
    ilo
    0.07
     het
    0.07
     яд
    0.07
    attr
    0.07
     force
    0.07
     tracking
    0.07
     дисп
    0.07
    Activations Density 0.010%

    No Known Activations