© 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 EvalsExportsinterp-engineNEWAPI 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. 70521
    Prev
    Next
    INDEX
    Explanations

    Wired internet connections

    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
     Clinic
    -0.09
     Esther
    -0.09
     Clínica
    -0.08
    /unit
    -0.08
     cud
    -0.08
     Cali
    -0.08
     Dritt
    -0.08
     Funds
    -0.08
     Howell
    -0.08
     dimensional
    -0.08
    POSITIVE LOGITS
     Ethernet
    0.09
     wired
    0.08
    .eb
    0.08
     edges
    0.08
     densely
    0.08
     chemo
    0.07
     kabel
    0.07
     ethernet
    0.07
     elektr
    0.07
     γρα
    0.07
    Activations Density 0.008%

    No Known Activations