Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 23627
    Prev
    Next
    INDEX
    Explanations

    direct

    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
     semesters
    -0.08
     naturelle
    -0.08
     unkompl
    -0.07
     Região
    -0.07
     Schmidt
    -0.07
     Clips
    -0.07
    ileged
    -0.07
     stade
    -0.07
     सहज
    -0.07
     épisode
    -0.07
    POSITIVE LOGITS
     marketing
    0.08
    .Console
    0.08
    ೋ
    0.08
    营销
    0.08
     television
    0.08
     ವಿರುದ್ಧ
    0.08
     التواصل
    0.08
    .router
    0.07
     correspondence
    0.07
    .Disable
    0.07
    Activations Density 0.008%

    No Known Activations