© 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. 3-RESID-POST-AA
    11. 13011
    Prev
    Next
    INDEX
    Explanations

    such

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     homo
    -0.08
     modifies
    -0.07
    중
    -0.07
     sort
    -0.07
    ambi
    -0.07
     Kam
    -0.07
    hom
    -0.07
    Modification
    -0.07
     Watt
    -0.07
     franc
    -0.07
    POSITIVE LOGITS
     eraan
    0.08
     handful
    0.08
     sov
    0.08
    estand
    0.08
     lok
    0.08
     зав
    0.07
     trov
    0.07
     Conde
    0.07
     Erin
    0.07
    لفة
    0.07
    Activations Density 0.002%

    No Known Activations