© 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. 68372
    Prev
    Next
    INDEX
    Explanations

    the

    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
    148
    -0.09
    ीं
    -0.08
     voorkeur
    -0.08
    \Not
    -0.08
    149
    -0.07
    258
    -0.07
    最快
    -0.07
    629
    -0.07
     schneller
    -0.07
     recherchez
    -0.07
    POSITIVE LOGITS
     towering
    0.09
    山
    0.09
     betrayal
    0.08
     slick
    0.08
     marble
    0.08
    queles
    0.08
     футб
    0.08
     ચાર
    0.07
     glowing
    0.07
    .Clock
    0.07
    Activations Density 0.021%

    No Known Activations