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. 53992
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     sebelum
    -0.08
     réun
    -0.08
     berita
    -0.08
     voordat
    -0.07
    纪委
    -0.07
    нд
    -0.07
    osse
    -0.07
    ция
    -0.07
    Этот
    -0.07
    арат
    -0.07
    POSITIVE LOGITS
     Models
    0.08
    ्वर
    0.08
     keyboards
    0.07
    ovsky
    0.07
    ulario
    0.07
     feed
    0.07
    ಂಬ
    0.07
     zabo
    0.07
    relationship
    0.07
     relatie
    0.07
    Activations Density 0.007%

    No Known Activations