© 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. 23-RESID-POST-AA
    11. 5902
    Prev
    Next
    INDEX
    Explanations

    say "¼ or ½"

    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
     ../../../
    -0.10
    emaakt
    -0.10
     tabel
    -0.10
     табли
    -0.09
     Tabellen
    -0.09
     बड़े
    -0.09
    095
    -0.09
     कॉल
    -0.09
     nagy
    -0.09
     Tables
    -0.09
    POSITIVE LOGITS
     pinch
    0.13
    ½
    0.11
    Pin
    0.11
     Pin
    0.10
    ¼
    0.10
    pin
    0.10
     sprinkle
    0.10
     Sprinkle
    0.09
    _pin
    0.09
     prick
    0.09
    Activations Density 0.013%

    No Known Activations