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. 78511
    Prev
    Next
    INDEX
    Explanations

    influencing or manipulating people

    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
     chaw
    -0.09
     zdję
    -0.08
    Antwort
    -0.08
     гара
    -0.08
     велосипед
    -0.08
     vatten
    -0.08
    Svar
    -0.08
    .ext
    -0.08
     پانی
    -0.08
    उत्तर
    -0.08
    POSITIVE LOGITS
     persuasion
    0.15
     propaganda
    0.13
     persuasive
    0.12
     manipul
    0.12
     manipulate
    0.12
     psychological
    0.12
    心理
    0.11
     manipulation
    0.11
     deception
    0.11
     Manip
    0.11
    Activations Density 0.064%

    No Known Activations