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. 106137
    Prev
    Next
    INDEX
    Explanations

    gem

    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
     Ler
    -0.09
     extent
    -0.09
     sling
    -0.08
     stance
    -0.08
    extent
    -0.08
     Perry
    -0.07
     sway
    -0.07
    惯
    -0.07
     receptive
    -0.07
     starch
    -0.07
    POSITIVE LOGITS
     craftsmanship
    0.09
     necklace
    0.09
     talents
    0.08
     shining
    0.08
     Necklace
    0.08
     handcrafted
    0.08
     quý
    0.08
    shade
    0.08
    dk
    0.08
     Minerals
    0.08
    Activations Density 0.010%

    No Known Activations