© 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. 15-RESID-POST-AA
    11. 16249
    Prev
    Next
    INDEX
    Explanations

    scene

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     using
    -0.08
    Using
    -0.08
     Using
    -0.08
    .Sequential
    -0.07
     sonunda
    -0.07
    ~=
    -0.07
     final
    -0.07
     menggunakan
    -0.07
    Сто
    -0.07
    .Handle
    -0.07
    POSITIVE LOGITS
    rịta
    0.10
    0.09
    某
    0.09
     (`
    0.09
    ીને
    0.09
    വുമായി
    0.08
    ათ
    0.08
    些
    0.08
    თან
    0.08
    rak
    0.08
    Activations Density 0.157%
    No Known Activations