Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 54007
    Prev
    Next
    INDEX
    Explanations

    conversational prompts

    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
     ...)↵
    -0.08
    /oder
    -0.07
     REG
    -0.07
    ...),
    -0.07
     enhver
    -0.07
     drugi
    -0.07
     regs
    -0.07
     Gug
    -0.07
     politi
    -0.07
    却
    -0.07
    POSITIVE LOGITS
    ।
    0.12
    。
    0.11
    。此外
    0.11
    。また
    0.10
    。另外
    0.10
    。在
    0.10
    ,那
    0.10
    。这
    0.10
    ,这
    0.10
    ,
    0.10
    Activations Density 0.586%

    No Known Activations