© 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. 11-RESID-POST-AA
    11. 75808
    Prev
    Next
    INDEX
    Explanations

    coordinate transformations

    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
     кур
    -0.08
    вей
    -0.08
     vein
    -0.08
     при
    -0.08
    ಿಯಾದ
    -0.07
     जोर
    -0.07
     हास
    -0.07
     Delivery
    -0.07
     chorus
    -0.07
    .chomp
    -0.07
    POSITIVE LOGITS
     coordinates
    0.12
     Coordinates
    0.11
    _coords
    0.11
     coordinate
    0.11
    Coordinates
    0.11
    Coordinate
    0.11
    Coord
    0.11
     coord
    0.10
    _coordinates
    0.10
     coordonnées
    0.10
    Activations Density 0.015%

    No Known Activations