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. 30738
    Prev
    Next
    INDEX
    Explanations

    Food ingredients

    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
    Cliente
    -0.08
    (and
    -0.07
    _BIG
    -0.07
    Bay
    -0.07
     thorough
    -0.07
    深入
    -0.07
    Assembler
    -0.07
    (the
    -0.07
    Analy
    -0.07
     econom
    -0.07
    POSITIVE LOGITS
     Marble
    0.09
     carriage
    0.09
     cmap
    0.09
    _cursor
    0.08
     Bowman
    0.08
    閱
    0.08
    ahn
    0.08
     Harr
    0.08
     Suk
    0.08
     pend
    0.08
    Activations Density 0.016%

    No Known Activations