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. 43235
    Prev
    Next
    INDEX
    Explanations

    find

    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
     dizziness
    -0.08
     ▼
    -0.08
     grandchildren
    -0.08
     iyang
    -0.08
     kong
    -0.08
     atof
    -0.08
     [+
    -0.08
     resin
    -0.08
    -btn
    -0.07
    萬
    -0.07
    POSITIVE LOGITS
     optimal
    0.11
     ceil
    0.10
     conject
    0.09
     maximal
    0.09
     configurations
    0.09
    Optimal
    0.09
    ceil
    0.09
     Optimal
    0.09
    optimal
    0.09
     combin
    0.08
    Activations Density 0.045%

    No Known Activations