© 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. 44751
    Prev
    Next
    INDEX
    Explanations

    potential

    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
     apron
    -0.08
     silly
    -0.08
     Erl
    -0.07
     instructions
    -0.07
     slap
    -0.07
     humorous
    -0.07
     liht
    -0.07
     counts
    -0.07
     shift
    -0.07
     puesta
    -0.07
    POSITIVE LOGITS
     talented
    0.11
    /high
    0.11
     geselect
    0.10
     ಪ್ರತಿಭ
    0.10
    人才
    0.10
    干部
    0.10
     shortlisted
    0.10
     intellect
    0.10
     Exceptional
    0.10
     kandidat
    0.10
    Activations Density 0.066%

    No Known Activations