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. 58793
    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
    ியம்
    -0.08
    ்மை
    -0.08
    esas
    -0.08
    uvwxyz
    -0.08
    ல்ல
    -0.08
     vos
    -0.08
     இருப்ப
    -0.07
     Gentleman
    -0.07
     pat
    -0.07
    ந்த
    -0.07
    POSITIVE LOGITS
                    ↵
    0.08
     Knock
    0.08
     độ
    0.08
     Зап
    0.07
     groceries
    0.07
     titled
    0.07
     inaugural
    0.07
    ,,
    0.07
    عنوان
    0.07
     Constitu
    0.07
    Activations Density 0.016%

    No Known Activations