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. 30528
    Prev
    Next
    INDEX
    Explanations

    0

    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
     enca
    -0.08
     lame
    -0.08
     puedan
    -0.07
     বিস্তারিত
    -0.07
     malo
    -0.07
     salesman
    -0.07
     j
    -0.07
     ves
    -0.07
    inese
    -0.07
     nivel
    -0.07
    POSITIVE LOGITS
     lockdown
    0.11
     COVID
    0.11
    COVID
    0.11
     пандем
    0.10
     pandémie
    0.10
     pandemia
    0.10
     pandemic
    0.10
     coronavirus
    0.09
     Covid
    0.09
     कोविड
    0.09
    Activations Density 0.019%

    No Known Activations