© 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. 129233
    Prev
    Next
    INDEX
    Explanations

    dry

    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
    	target
    -0.09
    64
    -0.08
    	actual
    -0.08
    	import
    -0.08
    _Target
    -0.08
    	This
    -0.08
    	The
    -0.07
    644
    -0.07
    	sign
    -0.07
    gir
    -0.07
    POSITIVE LOGITS
     stump
    0.10
    。截至
    0.08
     sè
    0.08
     läng
    0.08
     dri
    0.08
     ero
    0.07
     appelé
    0.07
    �
    0.07
     topper
    0.07
     پل
    0.07
    Activations Density 0.002%

    No Known Activations