Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 131006
    Prev
    Next
    INDEX
    Explanations

    dev

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DEVELOPMENT
    -0.08
    -moving
    -0.08
     developer
    -0.08
    Christian
    -0.08
    development
    -0.08
     developers
    -0.07
    developer
    -0.07
    developers
    -0.07
     ব্যাপ
    -0.07
     liik
    -0.07
    POSITIVE LOGITS
    /null
    0.11
     nodes
    0.10
    /mm
    0.10
    ノ
    0.10
     Nodes
    0.09
     ノ
    0.09
    urations
    0.09
    /v
    0.09
    _nv
    0.09
    _nodes
    0.09
    Activations Density 0.001%

    No Known Activations