© 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. 102663
    Prev
    Next
    INDEX
    Explanations

    Korean

    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
    oporosis
    -0.10
    ly
    -0.10
    此同时
    -0.09
    กัน
    -0.09
    式会社
    -0.09
    этому
    -0.09
    ellaneous
    -0.09
    া
    -0.08
    ых
    -0.08
    ेशा
    -0.08
    POSITIVE LOGITS
     શકે
    0.11
     सकते
    0.11
     सकती
    0.11
     सकता
    0.11
    mayı
    0.11
    으면
    0.11
    ಬಹುದು
    0.10
     سکتی
    0.10
    으며
    0.10
    acağını
    0.10
    Activations Density 0.006%

    No Known Activations