© 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. 95592
    Prev
    Next
    INDEX
    Explanations

    step, increment

    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
    čas
    -0.08
     nominate
    -0.08
     pauc
    -0.08
     Aura
    -0.07
    чив
    -0.07
     кандид
    -0.07
     saver
    -0.07
     långt
    -0.07
    Dónde
    -0.07
     nader
    -0.07
    POSITIVE LOGITS
     increments
    0.13
     incremental
    0.11
     diaria
    0.10
    Increment
    0.10
    씩
    0.10
    _increment
    0.10
    步
    0.09
     diária
    0.09
    increments
    0.09
    单位
    0.09
    Activations Density 0.032%

    No Known Activations