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. 77405
    Prev
    Next
    INDEX
    Explanations

    target

    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
     Swar
    -0.08
     解
    -0.07
     centrally
    -0.07
    _dims
    -0.07
     אס
    -0.07
     �
    -0.07
     ঘট
    -0.07
     revolving
    -0.07
     الطريقة
    -0.07
    luck
    -0.07
    POSITIVE LOGITS
     specifying
    0.09
    几年
    0.08
    Specify
    0.08
     TARGET
    0.08
     hedef
    0.08
    최
    0.08
     chois
    0.08
    指定
    0.08
    Platforms
    0.08
    TARGET
    0.08
    Activations Density 0.005%

    No Known Activations