© 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. 11-RESID-POST-AA
    6. 44694
    Prev
    Next
    INDEX
    Explanations

    single quote

    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
     lleno
    -0.09
    Processors
    -0.08
    igne
    -0.08
    .$$
    -0.07
     nearby
    -0.07
    -0.07
    _handlers
    -0.07
     remed
    -0.07
    凉
    -0.07
     san
    -0.07
    POSITIVE LOGITS
     Timestamp
    0.08
     Perf
    0.08
     wrongly
    0.08
     Sunset
    0.08
     pasangan
    0.08
    ted
    0.07
     pairing
    0.07
    roma
    0.07
     Pair
    0.07
     secon
    0.07
    Activations Density 0.002%

    No Known Activations