© 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. 54411
    Prev
    Next
    INDEX
    Explanations

    okes

    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
    личес
    -0.09
     במיוחד
    -0.09
    ಳೆ
    -0.08
     bookmark
    -0.08
    ánt
    -0.08
    אָט
    -0.08
     βιβ
    -0.08
    Sorting
    -0.08
    λω
    -0.08
    �
    -0.08
    POSITIVE LOGITS
    公布
    0.18
    宣布
    0.16
     announcements
    0.15
     announcing
    0.15
    发布
    0.14
     घोषणा
    0.14
    公告
    0.14
     spokesperson
    0.14
     발표
    0.14
    發布
    0.14
    Activations Density 0.216%

    No Known Activations