© 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. 69737
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    ικό
    -0.08
     volatil
    -0.07
     evaporation
    -0.07
     وحد
    -0.07
    conduct
    -0.07
     Kom
    -0.07
     gasto
    -0.07
    处
    -0.07
    avil
    -0.07
     ressembl
    -0.07
    POSITIVE LOGITS
     apron
    0.08
     Deux
    0.08
    Upload
    0.08
    HEST
    0.08
     réserver
    0.08
    itle
    0.08
    olic
    0.08
     horarios
    0.07
    .ids
    0.07
    .insets
    0.07
    Activations Density 0.001%

    No Known Activations