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. 12055
    Prev
    Next
    INDEX
    Explanations

    column values

    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
     Memory
    -0.08
     koron
    -0.07
     Gamma
    -0.07
     haqq
    -0.07
     Erstellung
    -0.07
     Intel
    -0.07
     ISR
    -0.07
     Pentagon
    -0.07
     char
    -0.07
     CUDA
    -0.07
    POSITIVE LOGITS
     entries
    0.13
    entries
    0.11
    _entries
    0.10
     Populate
    0.10
     Entries
    0.10
    值
    0.10
    Entries
    0.10
     DBNull
    0.09
    填写
    0.09
    .rich
    0.09
    Activations Density 0.016%

    No Known Activations