© 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. 113369
    Prev
    Next
    INDEX
    Explanations

    icos

    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
    裁
    -0.07
    <Option
    -0.07
    晚
    -0.07
     અમ
    -0.07
     Paral
    -0.07
     simmer
    -0.07
     Spaß
    -0.07
    ייש
    -0.06
     들
    -0.06
    orted
    -0.06
    POSITIVE LOGITS
    Concert
    0.08
    hedral
    0.07
     thro
    0.07
    idis
    0.07
    _th
    0.07
    消
    0.07
     xog
    0.07
     tali
    0.07
    Ul
    0.07
     theoretically
    0.07
    Activations Density 0.002%

    No Known Activations