© 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. 23-RESID-POST-AA
    11. 50847
    Prev
    Next
    INDEX
    Explanations

    kitchen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cannon
    -0.08
    fj
    -0.08
     bullion
    -0.07
     Telescope
    -0.07
    enis
    -0.07
    wald
    -0.07
     toxin
    -0.07
     federal
    -0.07
     minerai
    -0.07
     Leader
    -0.07
    POSITIVE LOGITS
     kitchen
    0.11
     keuken
    0.10
    厨房
    0.10
     коф
    0.10
     кух
    0.10
     winery
    0.09
     nutshell
    0.09
    剩
    0.09
     Küchen
    0.09
     veggie
    0.09
    Activations Density 0.008%

    No Known Activations