© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45456
    Prev
    Next
    INDEX
    Explanations

    Date and time code

    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
    FAX
    -0.08
    koop
    -0.08
     minced
    -0.08
    _mex
    -0.07
     mex
    -0.07
     flask
    -0.07
    Mex
    -0.07
     tomato
    -0.07
    tur
    -0.07
     econ
    -0.07
    POSITIVE LOGITS
     punctual
    0.12
     puntual
    0.09
    纪律
    0.08
     همچ
    0.08
     unquestionably
    0.08
    	bt
    0.08
     BT
    0.08
     bst
    0.08
     surprising
    0.07
     CET
    0.07
    Activations Density 0.001%

    No Known Activations