© 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. 7464
    Prev
    Next
    INDEX
    Explanations

    structure

    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
     Heide
    -0.08
    -0.08
    kezt
    -0.07
     companionship
    -0.07
    sortable
    -0.07
    uita
    -0.07
     corridors
    -0.07
    ты
    -0.07
    θηκε
    -0.07
     nötig
    -0.07
    POSITIVE LOGITS
     refinancing
    0.08
    鐘
    0.08
     prefab
    0.08
     zeg
    0.08
     verschen
    0.08
     Control
    0.08
     ပ
    0.08
     controleren
    0.08
    钟
    0.07
     لله
    0.07
    Activations Density 0.002%
    No Known Activations