© 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. 23-RESID-POST-AA
    11. 6187
    Prev
    Next
    INDEX
    Explanations

    correct

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Easily
    -0.12
     haverá
    -0.11
     terão
    -0.11
     facilement
    -0.10
     Would
    -0.10
     fácilmente
    -0.10
     आसानी
    -0.10
     facilmente
    -0.10
    에서도
    -0.10
    都会
    -0.10
    POSITIVE LOGITS
     correct
    0.31
     correcte
    0.29
     correcta
    0.28
     accurate
    0.28
     صحيح
    0.28
     सही
    0.28
     correcto
    0.28
     doğru
    0.27
     صحیح
    0.27
     correta
    0.27
    Activations Density 0.180%

    No Known Activations