© 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. 23-RESID-POST-AA
    11. 96240
    Prev
    Next
    INDEX
    Explanations

    say "direction"

    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
     pounds
    -0.07
     aged
    -0.07
     ages
    -0.07
     adag
    -0.07
     Ages
    -0.07
     ọnụ
    -0.07
    trizes
    -0.07
    税込
    -0.07
     Birthday
    -0.07
    ƙ
    -0.07
    POSITIVE LOGITS
     direction
    0.70
    _direction
    0.64
    direction
    0.64
    Direction
    0.64
    .direction
    0.62
     Direction
    0.62
    方向
    0.61
     directions
    0.59
     दिशा
    0.59
    (direction
    0.58
    Activations Density 0.244%

    No Known Activations