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

    Neuronpedia

    APICircuit 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. 12945
    Prev
    Next
    INDEX
    Explanations

    Carbon capture and utilization

    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
     UIResponder
    -0.08
     arrang
    -0.08
     beurte
    -0.08
    	box
    -0.08
     QVariant
    -0.08
    मार
    -0.08
     QApplication
    -0.08
     NSMutable
    -0.08
     moyo
    -0.08
     Võ
    -0.08
    POSITIVE LOGITS
     reutil
    0.10
    manufact
    0.09
     carbonation
    0.09
     manufacturing
    0.09
     recycle
    0.08
     precipitation
    0.08
     соедин
    0.08
     recic
    0.08
     reacting
    0.08
     seques
    0.08
    Activations Density 0.004%

    No Known Activations