© 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 EvalsExportsinterp-engineNEWAPI 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. 70800
    Prev
    Next
    INDEX
    Explanations

    Rushing out in the morning

    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
     instrumentation
    -0.08
    整改
    -0.07
     invasive
    -0.07
     Instr
    -0.07
    rud
    -0.07
     numbering
    -0.07
     árbit
    -0.07
    ils
    -0.07
     recursively
    -0.07
    ote
    -0.07
    POSITIVE LOGITS
     commuters
    0.15
     commuting
    0.13
     hectic
    0.13
     commute
    0.13
    忙
    0.12
     commuter
    0.12
     beruf
    0.12
     городской
    0.12
     onderweg
    0.11
     सुबह
    0.11
    Activations Density 0.140%

    No Known Activations