© 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. 11-RESID-POST-AA
    11. 47491
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     punching
    -0.07
    roid
    -0.07
    Hits
    -0.07
    -0.07
    Soc
    -0.07
    Punch
    -0.07
     synthesized
    -0.07
     punch
    -0.07
    umm
    -0.07
    Hit
    -0.06
    POSITIVE LOGITS
     вн
    0.09
    ализ
    0.08
     DISCLAIMER
    0.08
    谨
    0.08
     grans
    0.08
     تجهیزات
    0.08
     grafik
    0.08
    جلس
    0.08
     offsetof
    0.08
     기타
    0.08
    Activations Density 0.014%
    No Known Activations