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. 120205
    Prev
    Next
    INDEX
    Explanations

    statement

    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
    ML
    -0.07
     mà
    -0.07
     �
    -0.07
     ಆದ
    -0.07
    RARY
    -0.07
    IH
    -0.07
     excited
    -0.07
    NC
    -0.07
    自主
    -0.07
    imized
    -0.07
    POSITIVE LOGITS
     chuyện
    0.08
     Â
    0.07
     nasc
    0.07
    -chave
    0.07
     bets
    0.07
     Pon
    0.07
     Domino
    0.07
    AGEM
    0.07
    ример
    0.07
     olo
    0.07
    Activations Density 0.033%

    No Known Activations