© 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. 108541
    Prev
    Next
    INDEX
    Explanations

    analysis

    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
    .K
    -0.08
    携
    -0.07
    Fleet
    -0.07
    ộ
    -0.07
    이크
    -0.07
    (K
    -0.07
    .Z
    -0.07
     authenticate
    -0.07
    .R
    -0.07
     простой
    -0.07
    POSITIVE LOGITS
     Libya
    0.09
    .↵//↵
    0.08
    ."↵↵↵
    0.08
     hehe
    0.07
     Decorations
    0.07
    ®.
    0.07
     Them
    0.07
    ';↵↵↵
    0.07
     Lé
    0.07
     addictions
    0.07
    Activations Density 0.024%

    No Known Activations