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. 12116
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     linux
    -0.08
    albums
    -0.08
    Fld
    -0.08
     Gustavo
    -0.08
    Albums
    -0.07
     drejt
    -0.07
     možda
    -0.07
    learn
    -0.07
     hindu
    -0.07
    stid
    -0.07
    POSITIVE LOGITS
     uniformly
    0.11
     universally
    0.10
     uniform
    0.10
     everywhere
    0.09
     consistently
    0.09
    uniform
    0.09
    統
    0.09
     except
    0.09
     entries
    0.09
     pervasive
    0.08
    Activations Density 0.065%

    No Known Activations