Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 90121
    Prev
    Next
    INDEX
    Explanations

    y

    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
     butterknife
    -0.08
    rens
    -0.08
     충
    -0.08
     пу
    -0.08
    .prototype
    -0.07
     ආ
    -0.07
    orce
    -0.07
     صندوق
    -0.07
     Ribeiro
    -0.07
     البيضاء
    -0.07
    POSITIVE LOGITS
    oter
    0.09
     velho
    0.08
    _GEN
    0.08
     इंत
    0.08
    iffer
    0.07
    geries
    0.07
     exped
    0.07
    205
    0.07
     ethic
    0.07
    ger
    0.07
    Activations Density 0.001%

    No Known Activations