© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 114280
    Prev
    Next
    INDEX
    Explanations

    vertex/vertices

    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
     habil
    -0.08
     FIXME
    -0.08
     sosial
    -0.07
    place
    -0.07
    peed
    -0.07
     Quentin
    -0.07
     Collections
    -0.07
     daquele
    -0.07
    social
    -0.07
    -0.07
    POSITIVE LOGITS
     oluş
    0.08
     corners
    0.08
    हरी
    0.08
     perifer
    0.08
     demonstrating
    0.08
    והים
    0.07
     rectangles
    0.07
     típ
    0.07
     individually
    0.07
     linh
    0.07
    Activations Density 0.018%
    No Known Activations