© 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. 108267
    Prev
    Next
    INDEX
    Explanations

    terms

    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
    ರಿ
    -0.08
     theater
    -0.08
     ಅಥವಾ
    -0.08
     ಜೀವನ
    -0.08
     colonial
    -0.07
    或
    -0.07
     oppression
    -0.07
     ಸಂಪ
    -0.07
     ತಮ್ಮ
    -0.07
     curtains
    -0.07
    POSITIVE LOGITS
     crecimiento
    0.10
     Subse
    0.10
    增长
    0.10
     Growth
    0.10
     croissance
    0.10
     값을
    0.10
     growth
    0.10
    値
    0.10
     thereafter
    0.10
     Wachstum
    0.10
    Activations Density 0.050%

    No Known Activations