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. 42112
    Prev
    Next
    INDEX
    Explanations

    equals sign

    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
    救
    -0.09
    ouvre
    -0.07
     спас
    -0.07
    血
    -0.07
    谓
    -0.07
     ней
    -0.07
    lash
    -0.07
    応募
    -0.07
     euth
    -0.07
    ാർ
    -0.07
    POSITIVE LOGITS
     Beg
    0.09
     Builder
    0.08
     errado
    0.08
     Gson
    0.07
     antigo
    0.07
     chứa
    0.07
     ٺ
    0.07
     inconvenient
    0.07
     com
    0.07
     Colored
    0.07
    Activations Density 0.061%

    No Known Activations