© 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. 7-RESID-POST-AA
    11. 840
    Prev
    Next
    INDEX
    Explanations

    minutes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coax
    -0.08
     collectible
    -0.08
    493
    -0.08
     खाद
    -0.08
     zib
    -0.07
     informiert
    -0.07
     gasket
    -0.07
     informacije
    -0.07
     перен
    -0.07
     области
    -0.07
    POSITIVE LOGITS
    CPU
    0.09
     roster
    0.08
     throughput
    0.08
    曝光
    0.08
    _PAT
    0.08
     tenure
    0.08
    _cpu
    0.08
    -budget
    0.08
    Nas
    0.08
     Styles
    0.07
    Activations Density 0.013%

    No Known Activations