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. 49099
    Prev
    Next
    INDEX
    Explanations

    Cocktails

    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
     homeschooling
    -0.09
    Indent
    -0.08
     bullying
    -0.08
     hierro
    -0.08
    march
    -0.08
     பெரிய
    -0.08
    大片
    -0.08
    _inode
    -0.08
     Paral
    -0.08
    .children
    -0.08
    POSITIVE LOGITS
     cocktail
    0.11
     bartender
    0.11
     Cocktail
    0.11
     cocktails
    0.10
     напит
    0.10
     whiskey
    0.10
     whisky
    0.10
     tequila
    0.10
     bourbon
    0.09
     sip
    0.09
    Activations Density 0.040%

    No Known Activations