© 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. 1217
    Prev
    Next
    INDEX
    Explanations

    of

    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
     जे
    -0.08
     condens
    -0.08
    ipp
    -0.08
     digestion
    -0.07
    -paced
    -0.07
     disparities
    -0.07
     peaked
    -0.07
    _unref
    -0.07
     paced
    -0.07
     conver
    -0.07
    POSITIVE LOGITS
     sello
    0.08
     flourish
    0.08
     ág
    0.08
    liz
    0.08
    ually
    0.08
     lema
    0.07
     Variety
    0.07
     Bert
    0.07
    /ng
    0.07
     successo
    0.07
    Activations Density 0.005%

    No Known Activations