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. 44102
    Prev
    Next
    INDEX
    Explanations

    XML data extraction

    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
     experiential
    -0.10
     Lips
    -0.10
     sedent
    -0.09
     intox
    -0.09
     psyched
    -0.09
    ocial
    -0.09
     drunk
    -0.08
     pursuit
    -0.08
     drinks
    -0.08
     Potato
    -0.08
    POSITIVE LOGITS
    	xml
    0.21
    _xml
    0.21
    (xml
    0.21
     XML
    0.20
     xmlns
    0.19
    .xml
    0.19
    xml
    0.18
    _XML
    0.18
     xml
    0.18
    XML
    0.18
    Activations Density 0.015%

    No Known Activations