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. 112112
    Prev
    Next
    INDEX
    Explanations

    image generation/description

    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
     devons
    -0.09
    ctomy
    -0.08
     выбран
    -0.08
    çok
    -0.08
     Voraussetzungen
    -0.08
     максимально
    -0.08
     данной
    -0.08
     редко
    -0.08
     čist
    -0.07
     بذلك
    -0.07
    POSITIVE LOGITS
     Hobbit
    0.09
     miniature
    0.08
     Zoo
    0.08
    �
    0.08
     wadd
    0.08
     bubble
    0.08
     Hamlet
    0.08
     😂
    0.08
     Bubble
    0.08
     Unicorn
    0.07
    Activations Density 0.160%

    No Known Activations