© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49176
    Prev
    Next
    INDEX
    Explanations

    Delimited data

    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
     top
    -0.09
     Top
    -0.08
    top
    -0.08
    Top
    -0.07
     topo
    -0.07
    usan
    -0.07
    .top
    -0.07
    vall
    -0.07
    _top
    -0.07
     maximal
    -0.07
    POSITIVE LOGITS
     vận
    0.08
    _log
    0.07
     hice
    0.07
     ue
    0.07
    co
    0.07
     computadora
    0.07
    0.07
    ise
    0.07
     begeg
    0.07
     refining
    0.07
    Activations Density 0.021%
    No Known Activations