© 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. 5910
    Prev
    Next
    INDEX
    Explanations

    _re and re

    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
    mental
    -0.08
    REN
    -0.08
    nade
    -0.08
     rider
    -0.08
    Bike
    -0.08
    charger
    -0.08
     Cassidy
    -0.08
    white
    -0.08
     riding
    -0.08
    रेट
    -0.07
    POSITIVE LOGITS
     ashes
    0.08
    eches
    0.08
    thren
    0.08
    ধান
    0.08
    ഒരു
    0.08
     screams
    0.08
     premieres
    0.08
    isestä
    0.08
    erlijke
    0.08
    wendung
    0.08
    Activations Density 0.004%

    No Known Activations