© 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. 45757
    Prev
    Next
    INDEX
    Explanations

    Game dialogue/interaction

    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
     знач
    -0.08
    oci
    -0.08
     اف
    -0.07
     blijft
    -0.07
     کتاب
    -0.07
     Moi
    -0.07
     مس
    -0.07
    ’est
    -0.07
    ointer
    -0.07
     mno
    -0.07
    POSITIVE LOGITS
    hair
    0.09
    əc
    0.08
    Rock
    0.08
    hawk
    0.08
    дий
    0.08
    Nearby
    0.08
     Abe
    0.08
    Solar
    0.08
    Hong
    0.08
    дущ
    0.08
    Activations Density 0.023%

    No Known Activations