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. 52925
    Prev
    Next
    INDEX
    Explanations

    the

    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
     prer
    -0.08
     licensors
    -0.08
     fiat
    -0.08
    �
    -0.08
     নেত
    -0.08
     Advert
    -0.08
     RFC
    -0.08
     advertisers
    -0.07
     coupon
    -0.07
     Advertising
    -0.07
    POSITIVE LOGITS
     reorgan
    0.13
     rearr
    0.13
    収納
    0.13
     орнал
    0.11
    整理
    0.11
     Arrange
    0.11
     scattered
    0.11
     ورت
    0.11
     reordered
    0.10
     reorder
    0.10
    Activations Density 0.030%

    No Known Activations