© 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. 111186
    Prev
    Next
    INDEX
    Explanations

    origin

    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
     Ow
    -0.07
    Ow
    -0.07
    (book
    -0.07
    (normal
    -0.07
    �
    -0.07
     lng
    -0.07
     whales
    -0.07
     Edmond
    -0.07
     ow
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     sce
    0.09
     subordin
    0.08
    gewicht
    0.08
    gele
    0.08
    attie
    0.08
    vester
    0.08
    నే
    0.08
     FXMLLoader
    0.07
     deta
    0.07
     leve
    0.07
    Activations Density 0.012%

    No Known Activations