© 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. 30465
    Prev
    Next
    INDEX
    Explanations

    1 and 2

    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
    租
    -0.08
     nwee
    -0.08
    ierig
    -0.08
     Vice
    -0.08
     neil
    -0.07
     vener
    -0.07
     veille
    -0.07
    悉
    -0.07
     Rent
    -0.07
    нув
    -0.07
    POSITIVE LOGITS
    /id
    0.08
     advoc
    0.07
     प्रतिब
    0.07
     (%
    0.07
     (^
    0.07
     (=
    0.07
     Filename
    0.07
     (*.
    0.07
     potency
    0.07
     diámetro
    0.07
    Activations Density 0.006%

    No Known Activations