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. 44088
    Prev
    Next
    INDEX
    Explanations

    shrug

    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
     residential
    -0.08
     UCS
    -0.08
     résident
    -0.08
     Residential
    -0.08
     �
    -0.08
     Rabbit
    -0.08
     Dian
    -0.07
     Humane
    -0.07
     Volt
    -0.07
     कहल
    -0.07
    POSITIVE LOGITS
    🏼
    0.10
    🏻
    0.10
    然
    0.08
     appreci
    0.08
     пр
    0.08
    见
    0.07
    一下
    0.07
     pron
    0.07
    -ignore
    0.07
    =headers
    0.07
    Activations Density 0.001%

    No Known Activations