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. 58521
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     aldr
    -0.08
     akc
    -0.08
    abby
    -0.08
     पाया
    -0.07
    <Action
    -0.07
     lewe
    -0.07
    �
    -0.07
    lz
    -0.07
     ακ
    -0.07
     eam
    -0.07
    POSITIVE LOGITS
     ಫ
    0.08
     š
    0.08
     bộ
    0.08
     ಸೇ
    0.08
     根
    0.08
     fé
    0.07
     પ્રમ
    0.07
     ફ
    0.07
     ವಿಭಾಗ
    0.07
     Linux
    0.07
    Activations Density 0.001%

    No Known Activations