© 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. 3-RESID-POST-AA
    11. 1146
    Prev
    Next
    INDEX
    Explanations

    本文

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     شدن
    -0.08
     Pagan
    -0.08
    ودية
    -0.08
    த்த
    -0.07
    மிழ
    -0.07
    956
    -0.07
     уда
    -0.07
    باع
    -0.07
    -0.07
     habido
    -0.07
    POSITIVE LOGITS
     bern
    0.08
     sûr
    0.08
     Creating
    0.08
     ಕೈ
    0.08
     feeding
    0.08
     cock
    0.07
    เอง
    0.07
     respon
    0.07
     سير
    0.07
     య
    0.07
    Activations Density 0.005%
    No Known Activations