Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 130165
    Prev
    Next
    INDEX
    Explanations

    distance calculations

    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
     führte
    -0.08
     inol
    -0.07
     in
    -0.07
    .reader
    -0.07
    Ese
    -0.07
     masters
    -0.07
     formulier
    -0.07
    -proof
    -0.07
    �
    -0.07
    -0.07
    POSITIVE LOGITS
    ತ್ಪ
    0.09
    егов
    0.08
    pees
    0.08
     gow
    0.08
     despl
    0.08
    ethau
    0.08
    หว่าง
    0.08
    ോഗ
    0.08
    pload
    0.08
    cobra
    0.08
    Activations Density 0.112%

    No Known Activations