© 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. 31485
    Prev
    Next
    INDEX
    Explanations

    All

    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
     неправиль
    -0.08
     misguided
    -0.08
     réellement
    -0.08
     childhood
    -0.08
    selling
    -0.08
     kostenlos
    -0.08
    寓
    -0.08
     чуж
    -0.08
     guilt
    -0.08
     $("<
    -0.08
    POSITIVE LOGITS
     briefing
    0.11
     Commander
    0.09
    Ready
    0.09
     commencing
    0.09
     ready
    0.09
    ございます
    0.09
     underway
    0.08
    겠습니다
    0.08
    _ready
    0.08
     hereby
    0.08
    Activations Density 0.030%

    No Known Activations