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. 56221
    Prev
    Next
    INDEX
    Explanations

    lilies

    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
    bam
    -0.08
    ಗ
    -0.08
    _expand
    -0.08
     elites
    -0.08
    champ
    -0.08
    ומת
    -0.08
    Empty
    -0.08
    ಗಿನ
    -0.08
    ಬಹ
    -0.08
    شح
    -0.07
    POSITIVE LOGITS
    相关
    0.08
    282
    0.08
     Fender
    0.08
    组
    0.08
    関連
    0.07
     contraind
    0.07
     preventive
    0.07
     estimated
    0.07
    相關
    0.07
     toxic
    0.07
    Activations Density 0.001%

    No Known Activations