© 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. 129172
    Prev
    Next
    INDEX
    Explanations

    language and writing

    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
     reservas
    -0.09
     Managed
    -0.09
     RELEASE
    -0.08
    _MANAGER
    -0.08
     Release
    -0.08
     preached
    -0.08
     releases
    -0.08
     Szen
    -0.08
    -management
    -0.08
    [..
    -0.08
    POSITIVE LOGITS
     shapes
    0.12
    Shapes
    0.12
     shape
    0.12
     glyph
    0.12
    Glyph
    0.11
    .svg
    0.11
    (shape
    0.11
    Shape
    0.11
    _shapes
    0.11
     Shapes
    0.11
    Activations Density 0.026%

    No Known Activations