© 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. 30859
    Prev
    Next
    INDEX
    Explanations

    对

    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
    ádio
    -0.08
    ते
    -0.08
    idel
    -0.07
    Ori
    -0.07
     Jolie
    -0.07
     visceral
    -0.07
     Vid
    -0.07
     Lal
    -0.07
    细
    -0.07
    ದೇ
    -0.07
    POSITIVE LOGITS
    td
    0.09
    ்ப்பு
    0.08
     Partnerships
    0.08
    不上
    0.08
    остоя
    0.08
    Partners
    0.08
     partners
    0.08
    clas
    0.07
     conven
    0.07
     mellom
    0.07
    Activations Density 0.006%

    No Known Activations