© 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 EvalsExportsinterp-engineNEWAPI 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. 110242
    Prev
    Next
    INDEX
    Explanations

    1

    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
    =set
    -0.08
    means
    -0.07
    atischen
    -0.07
    global
    -0.07
    _global
    -0.07
    uite
    -0.07
    前
    -0.07
     السابق
    -0.07
    _↵↵
    -0.07
    567
    -0.07
    POSITIVE LOGITS
    �
    0.08
     SER
    0.08
     FER
    0.08
     Þ
    0.08
     FUCK
    0.08
     HAV
    0.07
    erkt
    0.07
    onse
    0.07
     KOM
    0.07
     త
    0.07
    Activations Density 0.021%

    No Known Activations