© 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. 44645
    Prev
    Next
    INDEX
    Explanations

    name

    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
    Dtos
    -0.09
    _items
    -0.08
    Jy
    -0.08
    爸
    -0.08
    骤
    -0.07
    ندية
    -0.07
    児
    -0.07
    맞
    -0.07
    浴
    -0.07
    _mes
    -0.07
    POSITIVE LOGITS
     visite
    0.07
     мастер
    0.07
     ess
    0.07
    .G
    0.07
     Robert
    0.07
    experimental
    0.07
     производ
    0.07
     Chair
    0.07
     dessus
    0.07
     quoi
    0.07
    Activations Density 0.010%

    No Known Activations