© 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. 129103
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
    名
    -0.09
    名前
    -0.08
     seamless
    -0.07
     pari
    -0.07
     radius
    -0.07
    振
    -0.07
     concours
    -0.07
     orbit
    -0.07
    仕
    -0.07
    取
    -0.07
    POSITIVE LOGITS
     Scientists
    0.10
    Scientists
    0.10
    cient
    0.09
     rechter
    0.08
    요일
    0.08
     peter
    0.08
    ［
    0.08
     Wochen
    0.08
      
    0.08
     Science
    0.08
    Activations Density 0.003%

    No Known Activations