© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50294
    Prev
    Next
    INDEX
    Explanations

    runtime

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oupes
    -0.08
     यूर
    -0.07
    нікі
    -0.07
    iginal
    -0.07
     amid
    -0.07
     progressing
    -0.07
     कृषि
    -0.07
     franch
    -0.07
     refreshing
    -0.07
     কৃষ
    -0.07
    POSITIVE LOGITS
     runtime
    0.61
    runtime
    0.55
    Runtime
    0.54
     Runtime
    0.53
    _runtime
    0.53
    .runtime
    0.50
    (runtime
    0.49
    -runtime
    0.46
     रन
    0.46
    _RUNTIME
    0.45
    Activations Density 0.061%

    No Known Activations