© 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. 3-RESID-POST-AA
    11. 943
    Prev
    Next
    INDEX
    Explanations

    content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Contr
    -0.08
     toku
    -0.07
     SIN
    -0.07
     contrary
    -0.07
    contr
    -0.07
     tir
    -0.07
     outsource
    -0.07
     verzorg
    -0.07
     outsourced
    -0.07
    သား
    -0.07
    POSITIVE LOGITS
    culos
    0.09
     Lama
    0.08
    ulkan
    0.08
     сообщает
    0.08
     Fernando
    0.08
     Electricity
    0.08
    jeta
    0.07
    朝
    0.07
    限
    0.07
     Husband
    0.07
    Activations Density 0.014%

    No Known Activations