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. 120215
    Prev
    Next
    INDEX
    Explanations

    authentication and anti-counterfeiting

    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
    chmod
    -0.09
     зарп
    -0.09
     ferie
    -0.09
     chmod
    -0.08
    polygon
    -0.08
     урок
    -0.08
    urlaub
    -0.08
     playoff
    -0.08
    .Timer
    -0.08
     shoreline
    -0.08
    POSITIVE LOGITS
     authenticity
    0.17
     Authentic
    0.14
    Authent
    0.14
     counterfeit
    0.13
    真实性
    0.13
     authentic
    0.13
     authent
    0.12
     genuine
    0.12
     verification
    0.12
    Verification
    0.11
    Activations Density 0.037%

    No Known Activations