Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 49300
    Prev
    Next
    INDEX
    Explanations

    hygiene and cleanliness

    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
    amwe
    -0.08
     друга
    -0.08
     расходов
    -0.08
    iliki
    -0.08
    elo
    -0.07
     fram
    -0.07
    गा
    -0.07
     беременности
    -0.07
    prov
    -0.07
     Prov
    -0.07
    POSITIVE LOGITS
     cleanliness
    0.11
     nettoyer
    0.11
     поверхности
    0.10
    _dirty
    0.10
     countertops
    0.10
     surfaces
    0.10
    Dirty
    0.10
     oppervlak
    0.10
     disinfect
    0.10
     гряз
    0.09
    Activations Density 0.047%

    No Known Activations