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. 60583
    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
    oup
    -0.08
     wooded
    -0.07
    utter
    -0.07
    PEc
    -0.07
    output
    -0.07
    -0.07
    multi
    -0.07
    orset
    -0.07
     somehow
    -0.07
    ির
    -0.07
    POSITIVE LOGITS
    ️⃣
    0.10
     👉
    0.10
     �
    0.09
    ക്രമ
    0.08
     �
    0.08
     этап
    0.08
     �
    0.08
     fra
    0.08
     वो
    0.08
     Gi
    0.08
    Activations Density 0.027%

    No Known Activations