© 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. 3162
    Prev
    Next
    INDEX
    Explanations

    -hand

    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
     relatives
    -0.08
     VL
    -0.07
    ت
    -0.07
     TJ
    -0.07
     patr
    -0.07
    185
    -0.07
     mechan
    -0.07
    vim
    -0.07
     matér
    -0.07
     мах
    -0.07
    POSITIVE LOGITS
     सी
    0.10
     מספר
    0.08
    在人
    0.08
     pessoal
    0.08
     الاجتما
    0.08
     testen
    0.08
     Ons
    0.07
     ebe
    0.07
     착
    0.07
     Bren
    0.07
    Activations Density 0.002%

    No Known Activations