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. 60855
    Prev
    Next
    INDEX
    Explanations

    code block

    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
     दृश्य
    -0.09
     גאר
    -0.09
    成绩
    -0.08
    ात्मक
    -0.08
     પાર
    -0.08
     draait
    -0.08
     Ian
    -0.08
     positives
    -0.08
     גבוה
    -0.08
    מור
    -0.08
    POSITIVE LOGITS
    ................................................................
    0.08
     whisper
    0.08
    018
    0.08
    000
    0.08
     whispered
    0.08
     preguntas
    0.08
    RS
    0.07
     shortening
    0.07
    СС
    0.07
    tt
    0.07
    Activations Density 0.006%

    No Known Activations