© 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. 8059
    Prev
    Next
    INDEX
    Explanations

    Mandarin Chinese

    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
     gant
    -0.08
    jat
    -0.08
     jap
    -0.08
    jalo
    -0.08
     Sof
    -0.08
    яш
    -0.07
    利来
    -0.07
     procéd
    -0.07
    हा
    -0.07
    加拿大
    -0.07
    POSITIVE LOGITS
     suffers
    0.11
     fails
    0.10
     छैन
    0.10
     இல்லை
    0.10
     محدود
    0.09
     ಕೊರ
    0.09
     придется
    0.09
     نمی
    0.09
    지가
    0.09
     제대로
    0.09
    Activations Density 0.157%

    No Known Activations