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. 11904
    Prev
    Next
    INDEX
    Explanations

    Speaking aloud

    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
     regards
    -0.08
     regard
    -0.08
    /info
    -0.07
     satellite
    -0.07
     officer
    -0.07
     particularly
    -0.07
     AAA
    -0.07
     info
    -0.07
    mitt
    -0.07
     beacon
    -0.07
    POSITIVE LOGITS
     aloud
    0.10
     mout
    0.10
     pecho
    0.09
    出来
    0.09
    �
    0.09
     outlining
    0.09
     شوي
    0.09
     cuadrados
    0.09
    出去
    0.09
     בזמן
    0.08
    Activations Density 0.088%

    No Known Activations