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. 29938
    Prev
    Next
    INDEX
    Explanations

    )(

    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
     provision
    -0.08
    [Index
    -0.08
    Tol
    -0.07
    గ్ర
    -0.07
     operation
    -0.07
    ిష
    -0.07
     Entries
    -0.07
     కార్య
    -0.07
     actually
    -0.07
    Provision
    -0.07
    POSITIVE LOGITS
     Messaging
    0.08
     slain
    0.07
     消
    0.07
     आहेत
    0.07
     �
    0.07
    ګي
    0.07
     matk
    0.07
     Christophe
    0.07
     ಹೆಸರು
    0.07
    illeurs
    0.07
    Activations Density 0.029%

    No Known Activations