© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 3015
    Prev
    Next
    INDEX
    Explanations

    then

    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
     खरी
    -0.08
     unfolding
    -0.07
     convinced
    -0.07
     मू
    -0.07
     interested
    -0.07
     theology
    -0.07
     लक्ष
    -0.07
    /social
    -0.07
     Aw
    -0.07
    理念
    -0.07
    POSITIVE LOGITS
     maj
    0.08
    杂
    0.08
     GV
    0.08
    itang
    0.08
     Terrace
    0.07
     gburugburu
    0.07
    odio
    0.07
     syd
    0.07
     episódio
    0.07
    MHz
    0.07
    Activations Density 0.006%

    No Known Activations