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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 53038
    Prev
    Next
    INDEX
    Explanations

    Reduce

    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
     MAIL
    -0.08
     voila
    -0.08
     Personally
    -0.08
    电话号码
    -0.08
    _light
    -0.07
     Favorite
    -0.07
    MAIL
    -0.07
     Convertible
    -0.07
    _Email
    -0.07
     verpflichtet
    -0.07
    POSITIVE LOGITS
     confusion
    0.13
     misunderstand
    0.13
     misconceptions
    0.12
     disparate
    0.11
     mis
    0.11
     भ्रम
    0.11
     inconsist
    0.10
     wasted
    0.10
     mism
    0.10
     misinformation
    0.10
    Activations Density 0.037%

    No Known Activations