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. 49268
    Prev
    Next
    INDEX
    Explanations

    Infection/Inflammation symptoms

    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
     Cow
    -0.08
    -house
    -0.08
     COD
    -0.08
     deriva
    -0.07
     carrière
    -0.07
     CSC
    -0.07
     famously
    -0.07
     career
    -0.07
     games
    -0.07
    -b
    -0.07
    POSITIVE LOGITS
     воспал
    0.12
     discolor
    0.11
     redness
    0.10
     التهاب
    0.10
    炎
    0.10
    itatis
    0.09
     andamento
    0.09
     mural
    0.09
     Angeb
    0.09
     Município
    0.09
    Activations Density 0.005%

    No Known Activations