© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91846
    Prev
    Next
    INDEX
    Explanations

    line break

    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
    (Utils
    -0.09
     musst
    -0.08
    Intr
    -0.08
     airborne
    -0.08
     beachfront
    -0.08
     яг
    -0.08
     intrac
    -0.08
     tablets
    -0.08
     হয়েছিল
    -0.08
    চিত
    -0.08
    POSITIVE LOGITS
     perform
    0.09
     comparator
    0.08
     gcd
    0.08
     Comparative
    0.08
     nitr
    0.08
    Perform
    0.08
    gré
    0.08
     GSM
    0.08
     mj
    0.07
    Comparison
    0.07
    Activations Density 0.001%

    No Known Activations