© 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. 29447
    Prev
    Next
    INDEX
    Explanations

    We

    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
    episodes
    -0.09
    Greek
    -0.08
    ె
    -0.08
    Accessory
    -0.08
     conosco
    -0.08
     suatu
    -0.08
     ateliers
    -0.07
    ๊ะ
    -0.07
     gpointer
    -0.07
    566
    -0.07
    POSITIVE LOGITS
    (ed
    0.08
    igis
    0.08
     sorgfält
    0.07
    uts
    0.07
     потр
    0.07
    /St
    0.07
    測
    0.07
    urk
    0.07
    licity
    0.07
     ldc
    0.07
    Activations Density 0.039%

    No Known Activations