© 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. 23-RESID-POST-AA
    11. 48803
    Prev
    Next
    INDEX
    Explanations

    powershell commands

    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
    	load
    -0.09
    	create
    -0.08
     obič
    -0.08
     Alma
    -0.08
    	default
    -0.08
    	delete
    -0.08
    	parse
    -0.08
    	append
    -0.08
     Collector
    -0.08
    .delete
    -0.08
    POSITIVE LOGITS
    Invoke
    0.17
     Invoke
    0.16
    (Get
    0.16
     New
    0.16
     Start
    0.15
     Get
    0.15
    Start
    0.15
    (New
    0.15
     Remove
    0.14
    Remove
    0.14
    Activations Density 0.005%

    No Known Activations