© 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. 70384
    Prev
    Next
    INDEX
    Explanations

    Fictional scenes continuations

    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
    swagger
    -0.08
     bewusst
    -0.08
    ALAR
    -0.08
     customized
    -0.08
    願
    -0.07
     wrapper
    -0.07
    раж
    -0.07
    wishlist
    -0.07
     meta
    -0.07
     зм
    -0.07
    POSITIVE LOGITS
    evt
    0.08
     jose
    0.07
    题
    0.07
    钮
    0.07
     Tus
    0.07
     Bus
    0.07
     event
    0.07
     huit
    0.07
    okt
    0.07
    东京
    0.07
    Activations Density 0.003%

    No Known Activations