© 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. 2814
    Prev
    Next
    INDEX
    Explanations

    name

    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
    Barcode
    -0.08
    ನ್ನ
    -0.08
     दूर
    -0.08
    Tras
    -0.08
    Artwork
    -0.08
    �
    -0.08
    Hay
    -0.07
     Whatsapp
    -0.07
    넷
    -0.07
     מר
    -0.07
    POSITIVE LOGITS
     verwe
    0.08
    撒
    0.08
    语
    0.08
     Sib
    0.08
    还是
    0.07
    erras
    0.07
    vr
    0.07
     дзя
    0.07
     ssl
    0.07
    赠
    0.07
    Activations Density 0.010%

    No Known Activations