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. 30564
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    없
    -0.08
     matéri
    -0.08
     anyar
    -0.08
     ڪري
    -0.08
     rétro
    -0.08
    يتي
    -0.08
    ীত
    -0.08
     많
    -0.08
     MART
    -0.08
    ань
    -0.08
    POSITIVE LOGITS
    0.08
     Schwanz
    0.07
     multiplied
    0.07
    970
    0.07
    ్�
    0.07
    471
    0.07
     proportional
    0.07
    960
    0.07
    111
    0.07
     transmission
    0.07
    Activations Density 0.170%

    No Known Activations