© 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. 19-RESID-POST-AA
    11. 20235
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    -start
    -0.10
     börja
    -0.10
    _START
    -0.10
    	Start
    -0.09
     diversion
    -0.09
     começar
    -0.09
    	start
    -0.09
     byrja
    -0.09
     empezar
    -0.09
     saor
    -0.09
    POSITIVE LOGITS
     suppose
    0.09
     we
    0.08
     jointly
    0.08
     which
    0.08
     subsequently
    0.08
    ,↵↵
    0.07
     induces
    0.07
     (\
    0.07
    .")↵
    0.07
     axes
    0.07
    Activations Density 0.012%

    No Known Activations