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. 15-RESID-POST-AA
    6. 19174
    Prev
    Next
    INDEX
    Explanations

    reward mechanisms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Webseite
    -0.09
    Website
    -0.08
    /property
    -0.08
     Website
    -0.08
     night's
    -0.08
    سبوع
    -0.08
    oggler
    -0.08
     ushort
    -0.08
    ਉ
    -0.08
    PHONE
    -0.08
    POSITIVE LOGITS
     mechanisms
    0.10
     zogenaamde
    0.09
     sogenannten
    0.09
     pathways
    0.08
     storytelling
    0.08
     “
    0.08
     sogenannte
    0.08
     several
    0.08
     foram
    0.08
     التس
    0.08
    Activations Density 0.005%

    No Known Activations