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. 23583
    Prev
    Next
    INDEX
    Explanations

    |

    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
    。因此
    -0.08
     составляет
    -0.08
    。所以
    -0.08
     rheumatoid
    -0.08
     cuc
    -0.07
     cuer
    -0.07
     окружа
    -0.07
     controleren
    -0.07
    /contact
    -0.07
    股
    -0.07
    POSITIVE LOGITS
    强调
    0.11
     emphasizing
    0.10
     강조
    0.10
     emphasize
    0.09
     emphas
    0.09
     تاکید
    0.08
     emphasizes
    0.08
     Это
    0.08
    fach
    0.08
     שמש
    0.08
    Activations Density 0.019%

    No Known Activations