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. 53075
    Prev
    Next
    INDEX
    Explanations

    Circles and distances

    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
    uminum
    -0.08
     colorful
    -0.08
     tabl
    -0.07
     جدول
    -0.07
    -0.07
     هذه
    -0.07
    leep
    -0.07
     مورد
    -0.07
     clicks
    -0.07
     Styl
    -0.07
    POSITIVE LOGITS
     tao
    0.11
     taong
    0.09
     oamen
    0.09
     människor
    0.09
     personen
    0.09
     chiều
    0.08
     בער
    0.08
     mensen
    0.08
     човек
    0.08
     personer
    0.08
    Activations Density 0.048%

    No Known Activations