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. 60896
    Prev
    Next
    INDEX
    Explanations

    starting, beginning, or over

    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
     references
    -0.08
     acus
    -0.08
    References
    -0.07
     bland
    -0.07
    Rate
    -0.07
     avo
    -0.07
    Conf
    -0.07
    Count
    -0.07
    _refs
    -0.07
    references
    -0.07
    POSITIVE LOGITS
     begann
    0.10
     journey
    0.10
     selesai
    0.10
     Begin
    0.09
     beginnings
    0.09
    _finished
    0.09
     början
    0.09
     Journey
    0.09
     began
    0.09
     begun
    0.09
    Activations Density 0.034%

    No Known Activations