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. 60956
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    -dia
    -0.08
    ल्प
    -0.08
     Dek
    -0.07
     Taschen
    -0.07
    Kho
    -0.07
     CEP
    -0.07
    ിലും
    -0.07
    ogli
    -0.07
    orro
    -0.07
    Für
    -0.07
    POSITIVE LOGITS
    ############
    0.08
     indik
    0.08
     ಇ
    0.08
     indic
    0.08
    เช
    0.08
    ................................................................
    0.08
    .column
    0.08
     поле
    0.08
     informace
    0.08
     daarin
    0.07
    Activations Density 0.005%

    No Known Activations