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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49423
    Prev
    Next
    INDEX
    Explanations

    say variations of "doc"

    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
     publications
    -0.09
     vir
    -0.08
     escolhas
    -0.08
    [])
    -0.08
     tracy
    -0.07
    egt
    -0.07
     eest
    -0.07
     Erdogan
    -0.07
     چى
    -0.07
     Incoming
    -0.07
    POSITIVE LOGITS
    .count
    0.09
     count
    0.09
    .Try
    0.09
    .doc
    0.09
    count
    0.08
    .contains
    0.08
     đoàn
    0.08
     intentar
    0.08
    	count
    0.08
    _count
    0.08
    Activations Density 0.001%

    No Known Activations