© 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. 25262
    Prev
    Next
    INDEX
    Explanations

    intermittent

    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
     ту
    -0.08
     peut
    -0.08
     beloved
    -0.08
     кезең
    -0.08
     konse
    -0.08
     lovable
    -0.08
     சீ
    -0.08
    なら
    -0.07
     cariño
    -0.07
     מוב
    -0.07
    POSITIVE LOGITS
    玩
    0.08
    очные
    0.08
    Jesu
    0.07
     articulation
    0.07
    odan
    0.07
    алт
    0.07
    ళ్ళ
    0.07
    造
    0.07
    ，不过
    0.07
    ablo
    0.07
    Activations Density 0.000%

    No Known Activations