© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 97758
    Prev
    Next
    INDEX
    Explanations

    subtle upward movement

    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
     slowly
    -0.09
     lentamente
    -0.08
     металл
    -0.08
     peaceful
    -0.08
     continually
    -0.08
     πολι
    -0.08
    -properties
    -0.08
     lớn
    -0.08
     continuously
    -0.08
     τέ
    -0.08
    POSITIVE LOGITS
    扬
    0.12
    挑
    0.10
    �
    0.09
    鼓
    0.09
    卷
    0.09
    舒
    0.08
     noen
    0.08
    抽
    0.08
    收
    0.08
    合
    0.08
    Activations Density 0.007%

    No Known Activations