© 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. 102616
    Prev
    Next
    INDEX
    Explanations

    online resources

    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
     meaningless
    -0.09
    -able
    -0.08
     gelingt
    -0.08
    lexible
    -0.08
    iende
    -0.07
     boshqa
    -0.07
     rompe
    -0.07
     verändert
    -0.07
     neka
    -0.07
    intern
    -0.07
    POSITIVE LOGITS
     للحصول
    0.12
     suelen
    0.12
     مراجعه
    0.11
     لديهم
    0.11
    бычно
    0.11
     suele
    0.11
     обычно
    0.10
     часто
    0.10
    िकारिक
    0.10
     usually
    0.10
    Activations Density 0.026%

    No Known Activations