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

    Neuronpedia

    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. 15-RESID-POST-AA
    11. 16551
    Prev
    Next
    INDEX
    Explanations

    bathrooms and toilets

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entusiasmo
    -0.09
    contra
    -0.08
    岁的
    -0.08
     વિરોધ
    -0.08
    populate
    -0.08
     двиг
    -0.07
     popul
    -0.07
     Bege
    -0.07
     enthousias
    -0.07
    -0.07
    POSITIVE LOGITS
     secluded
    0.14
     bathroom
    0.12
    厕所
    0.12
     suitable
    0.12
     conducive
    0.11
     toilettes
    0.11
     sanctuary
    0.11
     bathrooms
    0.11
     toilet
    0.11
     restroom
    0.10
    Activations Density 0.013%
    No Known Activations