© 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. 7537
    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
    -filled
    -0.09
     Talking
    -0.07
     ਨ
    -0.07
    chemist
    -0.07
    vr
    -0.07
    -te
    -0.07
     Atlético
    -0.07
    iffany
    -0.07
    ’équipe
    -0.07
    -column
    -0.07
    POSITIVE LOGITS
     servidores
    0.08
     ഉണ്ടായ
    0.08
    _MAIN
    0.08
     bair
    0.08
     ഉണ്ട
    0.08
    ين
    0.08
    HER
    0.07
     жоқ
    0.07
    errs
    0.07
     ciert
    0.07
    Activations Density 0.001%

    No Known Activations