© 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. 19-RESID-POST-AA
    11. 102782
    Prev
    Next
    INDEX
    Explanations

    Foreign language/words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     errone
    -0.08
     nila
    -0.08
     তারা
    -0.08
    że
    -0.07
    ̈
    -0.07
     त्यांनी
    -0.07
    šlo
    -0.07
     इन्ह
    -0.07
    يلات
    -0.07
    QUARE
    -0.07
    POSITIVE LOGITS
     একজন
    0.11
     seorang
    0.10
     ретінде
    0.10
    റായി
    0.10
     તરીકે
    0.10
     որպես
    0.09
     extraordinaire
    0.09
     experto
    0.09
     হিসেবে
    0.08
     म्हणून
    0.08
    Activations Density 0.145%

    No Known Activations