© 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. 2833
    Prev
    Next
    INDEX
    Explanations

    行

    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
     Neues
    -0.08
     TÜ
    -0.07
     výro
    -0.07
     قص
    -0.07
    heus
    -0.07
     zd
    -0.07
     makar
    -0.07
     Fy
    -0.07
     Fathers
    -0.07
     gray
    -0.07
    POSITIVE LOGITS
     Butler
    0.08
    �
    0.08
     CSI
    0.07
     заслуж
    0.07
     Scott
    0.07
     примен
    0.07
     estr
    0.07
     exquis
    0.07
    setting
    0.07
     Walker
    0.07
    Activations Density 0.002%

    No Known Activations