© 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. 102738
    Prev
    Next
    INDEX
    Explanations

    foreign language

    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
    어난
    -0.08
     każdego
    -0.08
     različ
    -0.07
    행
    -0.07
    ווי
    -0.07
    가지
    -0.07
    마다
    -0.07
    -0.07
    ను
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     وڌيڪ
    0.09
    こん
    0.09
    _more
    0.09
     更
    0.09
    adaxwey
    0.09
    jén
    0.09
    adaxweynaha
    0.09
    �ে
    0.09
    より
    0.09
     अधिक
    0.08
    Activations Density 0.001%
    No Known Activations