© 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. 70951
    Prev
    Next
    INDEX
    Explanations

    scene

    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
     quake
    -0.08
     مها
    -0.07
     қор
    -0.07
     hoop
    -0.07
     kabi
    -0.07
     quorum
    -0.07
     Mose
    -0.07
     spinner
    -0.07
     Lois
    -0.07
     Oy
    -0.07
    POSITIVE LOGITS
     unrealistic
    0.09
    末
    0.08
    /event
    0.08
     النهاية
    0.08
     Particular
    0.08
     temática
    0.08
    996
    0.07
     Vladimir
    0.07
    .tm
    0.07
    /Event
    0.07
    Activations Density 0.006%

    No Known Activations