© 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. 44537
    Prev
    Next
    INDEX
    Explanations

    his

    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
     London's
    -0.09
     gathered
    -0.08
    Paris
    -0.08
    πη
    -0.08
     cheap
    -0.08
     erotic
    -0.08
    lys
    -0.08
     barata
    -0.08
     paris
    -0.08
     پیر
    -0.08
    POSITIVE LOGITS
     varsity
    0.15
     freshman
    0.14
     NCAA
    0.13
     sophomore
    0.12
     freshmen
    0.12
     scholarships
    0.12
     ಕಾಲೇಜ
    0.11
     collegiate
    0.11
     ವಿದ್ಯಾರ್ಥ
    0.11
     coursework
    0.11
    Activations Density 0.130%

    No Known Activations