© 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. 7-RESID-POST-AA
    11. 976
    Prev
    Next
    INDEX
    Explanations

    gods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     linewidth
    -0.08
    NU
    -0.08
     tread
    -0.08
     verkeers
    -0.08
     Hampshire
    -0.08
     antidepress
    -0.08
     NI
    -0.07
    Shop
    -0.07
    店
    -0.07
    Kent
    -0.07
    POSITIVE LOGITS
     Buddhist
    0.10
     beings
    0.09
     supernatural
    0.09
     idol
    0.09
     idols
    0.09
     chen
    0.09
     Wrest
    0.09
     chakra
    0.09
    祝
    0.09
    願
    0.09
    Activations Density 0.212%

    No Known Activations