© 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. 3009
    Prev
    Next
    INDEX
    Explanations

    Image generation instructions

    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
     Bara
    -0.09
     Diploma
    -0.08
    uran
    -0.08
     detaine
    -0.08
    課
    -0.08
    ançais
    -0.08
    pren
    -0.08
     Corse
    -0.07
    anni
    -0.07
    sending
    -0.07
    POSITIVE LOGITS
    759
    0.09
     hou
    0.08
     hous
    0.07
     Hay
    0.07
     Kw
    0.07
     toca
    0.07
     kiko
    0.07
    _os
    0.07
     chơi
    0.07
     李
    0.07
    Activations Density 0.028%

    No Known Activations