© 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. 99802
    Prev
    Next
    INDEX
    Explanations

    angle of inclination

    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
    Feed
    -0.07
    Hub
    -0.07
     biomechanics
    -0.07
     proport
    -0.07
    Кроме
    -0.07
     AFF
    -0.07
    Concat
    -0.07
     תנ
    -0.07
     במ
    -0.07
     metrics
    -0.07
    POSITIVE LOGITS
     choque
    0.09
    ್ಯಾಯ
    0.08
     Salem
    0.08
    ೀಕ್ಷ
    0.08
     Clarence
    0.08
     الساعة
    0.08
     comienzo
    0.08
     ساعة
    0.08
    ಾಕ
    0.08
    inene
    0.08
    Activations Density 0.012%

    No Known Activations