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. 54164
    Prev
    Next
    INDEX
    Explanations

    in

    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
     wholes
    -0.10
     intox
    -0.08
     Ratings
    -0.08
     বর্ত
    -0.08
     percept
    -0.08
     nace
    -0.08
     preorder
    -0.08
     સં
    -0.07
     wahr
    -0.07
     teclado
    -0.07
    POSITIVE LOGITS
    स्थान
    0.10
     स्थान
    0.10
     planting
    0.09
    location
    0.08
     scattering
    0.08
     जगह
    0.08
     location
    0.08
    (location
    0.08
     located
    0.08
     locations
    0.08
    Activations Density 0.017%

    No Known Activations