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. 43183
    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
    örd
    -0.08
     wiele
    -0.08
     edição
    -0.08
     editions
    -0.08
     treated
    -0.07
     weisen
    -0.07
     dyst
    -0.07
    IELD
    -0.07
    üm
    -0.07
    …”↵↵
    -0.07
    POSITIVE LOGITS
     먼저
    0.08
    naires
    0.08
     Derecho
    0.08
    fonos
    0.07
     DERECHO
    0.07
     parte
    0.07
     derecho
    0.07
    zut
    0.07
     khỏi
    0.07
    logen
    0.07
    Activations Density 0.173%

    No Known Activations