© 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. 113267
    Prev
    Next
    INDEX
    Explanations

    period

    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
     cór
    -0.09
     Wikimedia
    -0.08
     Tableau
    -0.08
    .ST
    -0.08
    ércoles
    -0.08
    목
    -0.07
     basso
    -0.07
    EAN
    -0.07
    Bibli
    -0.07
     autonomia
    -0.07
    POSITIVE LOGITS
    所有
    0.08
     ভব
    0.07
     બધા
    0.07
     Po
    0.07
     bol
    0.07
     removing
    0.07
    raal
    0.07
     Ouro
    0.07
    ňuje
    0.07
     pumping
    0.07
    Activations Density 0.005%

    No Known Activations