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. 46710
    Prev
    Next
    INDEX
    Explanations

    intellectual property

    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
     izdel
    -0.08
     ocu
    -0.08
    īd
    -0.07
     Source
    -0.07
     نرم
    -0.07
     multiplying
    -0.07
    issão
    -0.07
    出
    -0.07
    ,nil
    -0.07
     pwodwi
    -0.07
    POSITIVE LOGITS
     theft
    0.09
    κές
    0.09
     Theft
    0.08
    盗
    0.08
     persegu
    0.08
     voyeur
    0.08
     vandal
    0.08
     επίπε
    0.08
     incentiv
    0.08
     hygiene
    0.08
    Activations Density 0.006%

    No Known Activations