© 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. 11-RESID-POST-AA
    11. 29270
    Prev
    Next
    INDEX
    Explanations

    counts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    youtu
    -0.08
     ante
    -0.08
     perched
    -0.07
    mate
    -0.07
     hipotec
    -0.07
    解除
    -0.07
     Latest
    -0.07
    -solving
    -0.07
     juvenile
    -0.07
    izen
    -0.07
    POSITIVE LOGITS
     counts
    0.15
    counts
    0.14
    _counts
    0.14
    Counts
    0.13
     tally
    0.12
     Counts
    0.11
     quantities
    0.10
     distributions
    0.10
     totals
    0.10
    <count
    0.10
    Activations Density 0.049%

    No Known Activations