© 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. 11-RESID-POST-AA
    11. 108589
    Prev
    Next
    INDEX
    Explanations

    pseudocode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mercial
    -0.08
    spot
    -0.08
    spark
    -0.07
     quoting
    -0.07
    plug
    -0.07
     vias
    -0.07
    transition
    -0.07
     بحق
    -0.07
    Fortunately
    -0.07
    wale
    -0.07
    POSITIVE LOGITS
    .Initialize
    0.10
    .initialize
    0.10
    算法
    0.10
     Initialize
    0.09
    Initialize
    0.09
     Algorithm
    0.09
    	initialize
    0.09
     उठा
    0.08
     algoritmo
    0.08
     PROCED
    0.08
    Activations Density 0.005%

    No Known Activations