© 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. 75798
    Prev
    Next
    INDEX
    Explanations

    daily

    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
    umping
    -0.08
    шими
    -0.08
    ump
    -0.08
     владель
    -0.07
    ವರು
    -0.07
    umped
    -0.07
    堵
    -0.07
     ponovno
    -0.07
     kişinin
    -0.07
    urricane
    -0.07
    POSITIVE LOGITS
     quotidienne
    0.09
    都有
    0.09
    都
    0.08
     hàng
    0.08
     সকালে
    0.08
     diária
    0.08
    都会
    0.08
    (?)
    0.08
     cotidiana
    0.08
     اليومية
    0.08
    Activations Density 0.033%

    No Known Activations