© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 47412
    Prev
    Next
    INDEX
    Explanations

    Tree of life

    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
     RESERVED
    -0.09
    атики
    -0.08
     SMTP
    -0.08
    veloper
    -0.08
     mesos
    -0.08
     FEMA
    -0.08
    ți
    -0.08
     NOAA
    -0.07
    污
    -0.07
     USPS
    -0.07
    POSITIVE LOGITS
     дерево
    0.12
     дерева
    0.11
     trees
    0.10
     árvore
    0.10
    .Tree
    0.10
     arbre
    0.10
     Trees
    0.09
     વૃ
    0.09
    -tree
    0.09
     Tree
    0.09
    Activations Density 0.017%

    No Known Activations