© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110413
    Prev
    Next
    INDEX
    Explanations

    date and time

    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
     constr
    -0.10
    搜尋
    -0.09
     bullied
    -0.08
    検索
    -0.08
     pitcher
    -0.08
    熟
    -0.07
    /jquery
    -0.07
     starter
    -0.07
     consideración
    -0.07
    搜索
    -0.07
    POSITIVE LOGITS
     timestamps
    0.18
     timestamp
    0.17
     Timestamp
    0.16
    Timestamp
    0.16
    (timestamp
    0.15
    _timestamp
    0.15
    timestamp
    0.15
    .Timestamp
    0.14
    .timestamp
    0.14
    timestamps
    0.13
    Activations Density 0.005%

    No Known Activations