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. 49661
    Prev
    Next
    INDEX
    Explanations

    publishing advances

    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
     үшін
    -0.08
     dildo
    -0.08
    ที่จะ
    -0.08
    เร
    -0.08
     какого
    -0.08
    ержащ
    -0.07
     scorch
    -0.07
     lubricant
    -0.07
     ос
    -0.07
     Toon
    -0.07
    POSITIVE LOGITS
    alle
    0.08
    Cells
    0.08
    Words
    0.07
    _words
    0.07
    雑
    0.07
    ೆಗಳು
    0.07
    digits
    0.07
    0.07
    编辑
    0.07
     nonce
    0.07
    Activations Density 0.002%

    No Known Activations