© 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. 47733
    Prev
    Next
    INDEX
    Explanations

    decided

    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
    age
    -0.08
     या
    -0.08
     वह
    -0.07
     виду
    -0.07
    pps
    -0.07
    CP
    -0.07
    Asp
    -0.07
    win
    -0.07
    Rd
    -0.07
     профессор
    -0.07
    POSITIVE LOGITS
    ว่าจะ
    0.09
     binge
    0.09
     wisely
    0.08
     honeymoon
    0.08
     Thierry
    0.08
     rằng
    0.08
     بشأن
    0.08
     wholeheartedly
    0.08
     Territorial
    0.07
     canton
    0.07
    Activations Density 0.030%

    No Known Activations