© 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. 68639
    Prev
    Next
    INDEX
    Explanations

    containment chamber descriptions

    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
     knack
    -0.09
     appréc
    -0.08
     مما
    -0.08
     ներկ
    -0.08
     CGRect
    -0.08
     معاملات
    -0.08
     cents
    -0.08
     ներկայ
    -0.08
     newfound
    -0.08
     նկ
    -0.08
    POSITIVE LOGITS
    -monitor
    0.09
     Monitoring
    0.09
     monitoring
    0.09
     тщательно
    0.08
    _monitor
    0.08
     monitored
    0.08
     kill
    0.08
    Monitoring
    0.08
    blind
    0.08
    kill
    0.08
    Activations Density 0.004%

    No Known Activations