© 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. 64429
    Prev
    Next
    INDEX
    Explanations

    code and typography

    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
     elektrom
    -0.09
     sedang
    -0.08
     Screenshot
    -0.08
     rubric
    -0.08
     السر
    -0.08
    -0.08
    snippet
    -0.08
    Grpc
    -0.08
    scr
    -0.08
     filmmaking
    -0.08
    POSITIVE LOGITS
     diverg
    0.09
     διαφο
    0.08
     inconsist
    0.08
     diver
    0.08
     distinctions
    0.07
    ユー
    0.07
     termos
    0.07
     tends
    0.07
     Diver
    0.07
    .extra
    0.07
    Activations Density 0.008%
    No Known Activations