© 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. 11-RESID-POST-AA
    11. 69140
    Prev
    Next
    INDEX
    Explanations

    overpayment

    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
     resolving
    -0.08
    hető
    -0.08
     refine
    -0.07
     Path
    -0.07
    OPTIONS
    -0.07
     subscriptions
    -0.07
     tarifs
    -0.07
     addressing
    -0.07
     fortsatt
    -0.07
     distinct
    -0.07
    POSITIVE LOGITS
     "***
    0.09
    ediend
    0.08
    	acc
    0.08
    够
    0.08
    	uint
    0.08
    	Date
    0.08
    	X
    0.08
    	event
    0.08
     كم
    0.08
    	QString
    0.08
    Activations Density 0.001%

    No Known Activations