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. 43867
    Prev
    Next
    INDEX
    Explanations

    u

    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
     Psi
    -0.08
    ondag
    -0.08
     Probably
    -0.08
     poss
    -0.07
     Well
    -0.07
     papa
    -0.07
    正确
    -0.07
     Steele
    -0.07
     Ito
    -0.07
     Пред
    -0.07
    POSITIVE LOGITS
     Bestand
    0.09
     ransom
    0.08
    AVE
    0.08
     SBC
    0.08
    রা
    0.08
    Materia
    0.08
    (hand
    0.08
    ่าว
    0.08
     roten
    0.08
     থাকবে
    0.08
    Activations Density 0.001%

    No Known Activations