© 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. 44737
    Prev
    Next
    INDEX
    Explanations

    you

    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
    VEVENT
    -0.08
     qon
    -0.07
     Nik
    -0.07
     vg
    -0.07
    _rectangle
    -0.07
     Bomb
    -0.07
    igure
    -0.07
     DVB
    -0.07
    ilent
    -0.07
     nol
    -0.07
    POSITIVE LOGITS
     عزیز
    0.09
     scarce
    0.09
     ikaw
    0.09
    安心
    0.08
     deserving
    0.08
     underserved
    0.08
     మా
    0.07
     coming
    0.07
     compter
    0.07
    "path
    0.07
    Activations Density 0.100%

    No Known Activations