© 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. 95797
    Prev
    Next
    INDEX
    Explanations

    y

    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
     defensive
    -0.08
    -reset
    -0.08
     fut
    -0.07
     фав
    -0.07
     selet
    -0.07
     लॉक
    -0.07
     ivez
    -0.07
    іт
    -0.07
     MOQ
    -0.07
     ఇ
    -0.07
    POSITIVE LOGITS
    =y
    0.10
    _firestore
    0.09
    ,y
    0.09
    纬
    0.09
    	y
    0.09
    yd
    0.08
    _lat
    0.08
    ','=
    0.08
    =r
    0.08
    _CONTROLLER
    0.08
    Activations Density 0.014%

    No Known Activations