© 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. 77920
    Prev
    Next
    INDEX
    Explanations

    day

    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
     terribly
    -0.08
    ylum
    -0.08
    련
    -0.08
    EClass
    -0.08
     horribly
    -0.07
    Finally
    -0.07
     imme
    -0.07
    ラム
    -0.07
     lighten
    -0.07
    錯
    -0.07
    POSITIVE LOGITS
     Minutes
    0.08
     минут
    0.08
     woo
    0.08
     год
    0.08
    >):
    0.08
     sejak
    0.08
     Autonomous
    0.08
     plut
    0.08
    علن
    0.07
     Activities
    0.07
    Activations Density 0.008%

    No Known Activations