© 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. 3-RESID-POST-AA
    11. 2827
    Prev
    Next
    INDEX
    Explanations

    -up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tú
    -0.08
     rod
    -0.08
    Separ
    -0.07
     KC
    -0.07
    通
    -0.07
     ramb
    -0.07
    Rod
    -0.07
     Kod
    -0.07
     通
    -0.07
    透
    -0.07
    POSITIVE LOGITS
     aigu
    0.08
     театр
    0.08
     на
    0.08
     облад
    0.08
     Richard
    0.08
    dp
    0.07
     учетом
    0.07
    ting
    0.07
     şə
    0.07
     holy
    0.07
    Activations Density 0.017%

    No Known Activations