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. 56177
    Prev
    Next
    INDEX
    Explanations

    Stealing or taking

    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
    portrait
    -0.08
     ondersteunen
    -0.08
    etele
    -0.08
     rendelkez
    -0.07
     betrouw
    -0.07
     Arag
    -0.07
    ্যার
    -0.07
     orientar
    -0.07
    াপে
    -0.07
    Appear
    -0.07
    POSITIVE LOGITS
     चोरी
    0.16
     theft
    0.16
     steals
    0.15
    盗
    0.15
     unauthorized
    0.14
     stealing
    0.13
    偷
    0.13
     Theft
    0.13
    偷偷
    0.13
     illegally
    0.13
    Activations Density 0.040%

    No Known Activations