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. 97046
    Prev
    Next
    INDEX
    Explanations

    Pipeline and column

    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
    isser
    -0.08
     berdi
    -0.08
     shapes
    -0.08
    ిన్
    -0.08
    Shapes
    -0.07
     façon
    -0.07
     NUnit
    -0.07
    .gdx
    -0.07
    ICO
    -0.07
     Balls
    -0.07
    POSITIVE LOGITS
     Pipeline
    0.13
    Pipeline
    0.12
     remainder
    0.12
    .compose
    0.11
    _pipeline
    0.11
    _column
    0.11
     Column
    0.11
    ipeline
    0.11
    _PIPE
    0.10
    Column
    0.10
    Activations Density 0.001%

    No Known Activations