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

    Neuronpedia

    Jacobian LensNEW
    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. 113465
    Prev
    Next
    INDEX
    Explanations

    Numbers with leading zeros

    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
     ethics
    -0.08
     leitores
    -0.08
     relocation
    -0.07
     Buyers
    -0.07
     ethical
    -0.07
     nexus
    -0.07
     shoppers
    -0.07
     stö
    -0.07
     ומש
    -0.07
    伦理
    -0.07
    POSITIVE LOGITS
    inderella
    0.09
    Robin
    0.08
     strictly
    0.08
    라도
    0.08
     بط
    0.08
     seriously
    0.08
     Telef
    0.08
     traditionnel
    0.08
     lavage
    0.08
     traditionally
    0.08
    Activations Density 0.011%

    No Known Activations