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. 52976
    Prev
    Next
    INDEX
    Explanations

    file management/editing

    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
    >{@
    -0.07
     queue
    -0.07
    ')).
    -0.07
     sept
    -0.07
     conden
    -0.07
     tilbyder
    -0.07
    '),↵
    -0.07
    Furthermore
    -0.07
     rowspan
    -0.07
    г
    -0.07
    POSITIVE LOGITS
     Naming
    0.10
     Originals
    0.10
     documenting
    0.10
     همیشه
    0.09
     naming
    0.09
     Clearly
    0.09
    Naming
    0.09
     originals
    0.09
     precautions
    0.09
    整理
    0.09
    Activations Density 0.009%

    No Known Activations