© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 23-RESID-POST-AA
    11. 50116
    Prev
    Next
    INDEX
    Explanations

    Media converters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    公平
    -0.08
     cooperation
    -0.08
     postal
    -0.08
     deadlines
    -0.08
     reconciliation
    -0.08
     fejl
    -0.07
     håll
    -0.07
    ữu
    -0.07
    stå
    -0.07
    ær
    -0.07
    POSITIVE LOGITS
     Zam
    0.09
     atrav
    0.08
    	fmt
    0.08
     Media
    0.08
     Tips
    0.07
     йө
    0.07
    .media
    0.07
     रुप
    0.07
     मीडिया
    0.07
    	LOG
    0.07
    Activations Density 0.001%

    No Known Activations