© 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. 96571
    Prev
    Next
    INDEX
    Explanations

    Right parentheses

    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
     angle
    -0.09
     angu
    -0.08
    .angle
    -0.08
     cosine
    -0.08
     sinus
    -0.08
     vrijheid
    -0.08
     Angle
    -0.08
     limón
    -0.08
    真人
    -0.08
     angled
    -0.08
    POSITIVE LOGITS
     floor
    0.21
     ceil
    0.21
    ceil
    0.20
    .floor
    0.20
     floors
    0.20
    floor
    0.19
    _floor
    0.19
    Floor
    0.18
     flooring
    0.18
     Floor
    0.17
    Activations Density 0.108%

    No Known Activations