© 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. 2890
    Prev
    Next
    INDEX
    Explanations

    Trade

    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
    -0.08
     ak
    -0.08
     él
    -0.07
     bol
    -0.07
     verre
    -0.07
    잡
    -0.07
     académ
    -0.07
     Furn
    -0.07
    ಲ್ಲಿ
    -0.07
     dyst
    -0.07
    POSITIVE LOGITS
    changing
    0.08
     iid
    0.07
     creating
    0.07
     attending
    0.07
    Changing
    0.07
     limiting
    0.07
     enhancing
    0.07
     terreno
    0.07
    iox
    0.07
     ऐ
    0.07
    Activations Density 0.003%
    No Known Activations