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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 41
    Prev
    Next
    INDEX
    Explanations

    sum

    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
    çok
    -0.08
     hostility
    -0.08
     Morocco
    -0.08
     Epidemi
    -0.08
     Vorteil
    -0.08
     Horde
    -0.08
     Minis
    -0.08
     epidemi
    -0.08
    になる
    -0.08
     konflikt
    -0.08
    POSITIVE LOGITS
     తర
    0.08
    hr
    0.07
    SYS
    0.07
     delightful
    0.07
     delights
    0.07
     timing
    0.07
     थिए
    0.07
     прод
    0.07
    오는
    0.07
     odont
    0.07
    Activations Density 0.002%

    No Known Activations