© 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. 97325
    Prev
    Next
    INDEX
    Explanations

    Indonesian text involving skills

    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
     aktu
    -0.10
    üsü
    -0.08
    κό
    -0.08
    \Extension
    -0.08
    ้อ
    -0.08
    ckte
    -0.07
    чу
    -0.07
     Cu
    -0.07
    ώντας
    -0.07
    ół
    -0.07
    POSITIVE LOGITS
    ampilan
    0.09
    uk
    0.08
     army
    0.08
    azed
    0.07
    azeera
    0.07
    Authorities
    0.07
    aze
    0.07
    0.07
    ikip
    0.07
     convictions
    0.07
    Activations Density 0.003%
    No Known Activations