© 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. 113628
    Prev
    Next
    INDEX
    Explanations

    toiletries

    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
    ITUDE
    -0.08
     typename
    -0.08
     satellite
    -0.07
     प्रतिब
    -0.07
     Ley
    -0.07
    orithms
    -0.07
    _Tag
    -0.07
     caste
    -0.07
     الدر
    -0.07
     rescu
    -0.07
    POSITIVE LOGITS
     toothpaste
    0.14
     toiletries
    0.13
     toilette
    0.13
     toothbrush
    0.11
     Toilet
    0.11
     Toile
    0.10
     toilettes
    0.10
     shampoo
    0.10
     туал
    0.10
     higiene
    0.09
    Activations Density 0.052%

    No Known Activations