© 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. 19-RESID-POST-AA
    11. 102530
    Prev
    Next
    INDEX
    Explanations

    say "133"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gutters
    -0.08
     aislamiento
    -0.08
    ті
    -0.08
     eventdata
    -0.07
     ukuy
    -0.07
     scattered
    -0.07
     upward
    -0.07
     deletion
    -0.07
     endpoints
    -0.07
     desired
    -0.07
    POSITIVE LOGITS
    	char
    0.09
    	m
    0.09
    _INCLUDE
    0.09
    	strcpy
    0.09
     Discuss
    0.09
     хора
    0.08
    	case
    0.08
     άνθρω
    0.08
     discusses
    0.08
    	login
    0.08
    Activations Density 0.001%

    No Known Activations