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. 15-RESID-POST-AA
    6. 19138
    Prev
    Next
    INDEX
    Explanations

    imperative statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onderscheiden
    -0.09
    ൂര്
    -0.08
    ൂർ
    -0.08
     uniek
    -0.08
    olvers
    -0.07
     hierdoor
    -0.07
     therefore
    -0.07
     vượt
    -0.07
     daardoor
    -0.07
     zowel
    -0.07
    POSITIVE LOGITS
     alternatively
    0.13
     вовсе
    0.13
     prostu
    0.12
     alternativ
    0.12
    ก็
    0.11
     simplemente
    0.11
     simplement
    0.11
     outright
    0.11
     thereof
    0.11
     פשוט
    0.11
    Activations Density 0.200%

    No Known Activations