© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 69060
    Prev
    Next
    INDEX
    Explanations

    Directional light

    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
     formes
    -0.08
     залеж
    -0.07
     смотр
    -0.07
    生态
    -0.07
    so
    -0.07
     types
    -0.07
     parfaitement
    -0.07
     они
    -0.07
     terro
    -0.07
    亚
    -0.07
    POSITIVE LOGITS
     Edmonton
    0.09
     Hod
    0.08
     Ansch
    0.08
     Ted
    0.08
     Ruth
    0.08
     Gail
    0.08
    rafted
    0.08
     Carolyn
    0.08
     Hancock
    0.08
    Ted
    0.07
    Activations Density 0.000%

    No Known Activations