© 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. 13150
    Prev
    Next
    INDEX
    Explanations

    442

    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
     gur
    -0.08
     upstream
    -0.07
     ধার
    -0.07
    331
    -0.07
    חרות
    -0.07
    editable
    -0.07
     lethal
    -0.07
    occur
    -0.07
     சேர
    -0.07
    -cont
    -0.07
    POSITIVE LOGITS
    訪
    0.09
     bal
    0.08
     Moo
    0.08
    TO
    0.08
     Tore
    0.07
     Menn
    0.07
     Cow
    0.07
    anek
    0.07
    ень
    0.07
    mj
    0.07
    Activations Density 0.004%

    No Known Activations