© 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. 11-RESID-POST-AA
    11. 69366
    Prev
    Next
    INDEX
    Explanations

    of

    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
     underst
    -0.07
    .scope
    -0.07
    (parts
    -0.07
    (mon
    -0.07
    _client
    -0.07
     Ska
    -0.07
     erhöhen
    -0.07
    ต้น
    -0.07
     Grund
    -0.07
    .Highlight
    -0.07
    POSITIVE LOGITS
    fully
    0.10
    ifice
    0.10
     искусства
    0.10
    matig
    0.09
    麗
    0.09
     acontecer
    0.09
     कला
    0.09
    matige
    0.08
     antis
    0.08
    fulness
    0.08
    Activations Density 0.014%

    No Known Activations