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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 77252
    Prev
    Next
    INDEX
    Explanations

    anti-money laundering, terrorism

    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
     manhã
    -0.08
     zählen
    -0.08
     enums
    -0.07
     crowns
    -0.07
     Herzen
    -0.07
     ache
    -0.07
     presenti
    -0.07
     Oh
    -0.07
     aanwezig
    -0.07
     stap
    -0.07
    POSITIVE LOGITS
    融资
    0.12
    犯罪
    0.12
     ilíc
    0.11
    非法
    0.11
     illicit
    0.11
     financiamento
    0.11
     financing
    0.11
    诈骗
    0.10
     незакон
    0.10
    资金
    0.10
    Activations Density 0.007%

    No Known Activations