© 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. 79093
    Prev
    Next
    INDEX
    Explanations

    name

    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
    aving
    -0.08
    дар
    -0.08
     hep
    -0.08
     varm
    -0.08
     брать
    -0.07
     mirrors
    -0.07
     creams
    -0.07
    shal
    -0.07
     जाह
    -0.07
    板
    -0.07
    POSITIVE LOGITS
    nie
    0.09
     nasze
    0.08
    Н
    0.08
     oswa
    0.07
     dude
    0.07
     greatness
    0.07
     الواحد
    0.07
    /fw
    0.07
    elé
    0.07
     somet
    0.07
    Activations Density 0.008%

    No Known Activations