© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6611
    Prev
    Next
    INDEX
    Explanations

    street settings

    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
    имый
    -0.09
    .idx
    -0.08
    הליך
    -0.08
     וד
    -0.08
     autant
    -0.08
    [ix
    -0.08
    имые
    -0.08
     دولة
    -0.08
     vårt
    -0.08
    ्यमंत्री
    -0.08
    POSITIVE LOGITS
    wn
    0.12
    etsy
    0.09
    etsa
    0.08
    ets
    0.08
    WN
    0.08
    igth
    0.08
    gh
    0.08
    ung
    0.08
    agraph
    0.08
    ంగ
    0.08
    Activations Density 0.001%

    No Known Activations