© 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. 64469
    Prev
    Next
    INDEX
    Explanations

    hobbies

    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
     корпоратив
    -0.08
     следующий
    -0.08
     cáo
    -0.08
     표
    -0.07
     trabalham
    -0.07
     arbeit
    -0.07
     지급
    -0.07
     Corporate
    -0.07
     القي
    -0.07
     arbejder
    -0.07
    POSITIVE LOGITS
     hobbies
    0.26
     hobby
    0.19
     extracurricular
    0.16
     loisirs
    0.16
     passions
    0.15
     pursuits
    0.14
     recreational
    0.14
     leisure
    0.14
     pastime
    0.14
    兴趣
    0.13
    Activations Density 0.087%

    No Known Activations