© 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. 99497
    Prev
    Next
    INDEX
    Explanations

    distance

    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
     row
    -0.09
    _row
    -0.08
     Crow
    -0.08
    row
    -0.07
    	row
    -0.07
     Row
    -0.07
     ]
    -0.07
    .row
    -0.07
    _ROW
    -0.07
     رج
    -0.07
    POSITIVE LOGITS
     दूरी
    0.10
     расстоя
    0.09
    Oxford
    0.09
     чуж
    0.09
     দূ
    0.09
     distances
    0.09
    Nós
    0.09
    Distance
    0.09
    distance
    0.09
     interdiscip
    0.08
    Activations Density 0.010%

    No Known Activations