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. 30626
    Prev
    Next
    INDEX
    Explanations

    image generation prompts

    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
     Beaut
    -0.08
     കേ
    -0.08
    -interest
    -0.08
     Tune
    -0.08
    -that
    -0.08
     dumping
    -0.08
     vốn
    -0.08
     രക്ഷ
    -0.08
     Dej
    -0.08
    治
    -0.07
    POSITIVE LOGITS
     elliptical
    0.08
     pulse
    0.08
    Head
    0.07
    Worldwide
    0.07
    0.07
     cà
    0.07
    �
    0.07
    �
    0.07
     cannabis
    0.07
    Developer
    0.07
    Activations Density 0.003%

    No Known Activations