© 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. 15-RESID-POST-AA
    11. 16426
    Prev
    Next
    INDEX
    Explanations

    assigning values

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -pol
    -0.07
     worldwide
    -0.07
    unicode
    -0.07
     guerras
    -0.07
     fabricantes
    -0.07
     unicode
    -0.07
     smoother
    -0.07
     beyond
    -0.07
    GLOBAL
    -0.07
    -global
    -0.07
    POSITIVE LOGITS
     Assigned
    0.09
    赋
    0.09
    choose
    0.09
    	assign
    0.09
     assign
    0.09
     assignments
    0.09
    .Assign
    0.09
    Assignment
    0.09
    ensko
    0.08
    Assign
    0.08
    Activations Density 0.009%

    No Known Activations