© 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. 102488
    Prev
    Next
    INDEX
    Explanations

    say "possible"

    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
    	data
    -0.11
    	has
    -0.09
    _data
    -0.09
    146
    -0.09
    	border
    -0.09
    	Data
    -0.09
    ाढ़
    -0.08
    Carthy
    -0.08
     Städ
    -0.08
    	debug
    -0.08
    POSITIVE LOGITS
     possible
    0.18
     ಸಾಧ್ಯ
    0.18
     mogelijke
    0.18
     возмож
    0.17
     магчым
    0.17
    _possible
    0.17
    possible
    0.17
     الممكن
    0.17
     possibile
    0.17
     можлив
    0.17
    Activations Density 0.033%

    No Known Activations