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. 88146
    Prev
    Next
    INDEX
    Explanations

    from

    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
    spam
    -0.08
     Frankfurt
    -0.08
     dubious
    -0.07
     нәр
    -0.07
     degraded
    -0.07
    speech
    -0.07
     THAT
    -0.07
     алып
    -0.07
    -0.07
    intptr
    -0.07
    POSITIVE LOGITS
    预测
    0.11
    计划
    0.09
    预
    0.09
    预计
    0.09
    规划
    0.09
    ued
    0.09
     prediction
    0.09
     आद
    0.08
     ذكر
    0.08
     verwachting
    0.08
    Activations Density 0.006%

    No Known Activations