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. 98152
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
     bosh
    -0.08
     б
    -0.08
     Ben
    -0.08
     Б
    -0.08
    ungs
    -0.08
     Gale
    -0.08
     тво
    -0.08
     ben
    -0.08
     Bö
    -0.08
    ぜ
    -0.08
    POSITIVE LOGITS
    Triangle
    0.08
    _DATA
    0.08
    OVED
    0.08
    File
    0.08
    -file
    0.08
    _Data
    0.08
    /q
    0.07
    (Array
    0.07
    /img
    0.07
    .mat
    0.07
    Activations Density 0.000%

    No Known Activations