© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 108519
    Prev
    Next
    INDEX
    Explanations

    Hattie

    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
     adapting
    -0.08
     સમ
    -0.08
    олня
    -0.08
    .datetime
    -0.08
    ,北京
    -0.07
     flavor
    -0.07
    classic
    -0.07
     ವಿನ
    -0.07
    лика
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    Ht
    0.07
    zame
    0.07
     Speaker
    0.07
     Mek
    0.07
     Projection
    0.07
     Concord
    0.07
    hette
    0.07
     Cair
    0.07
     Constit
    0.07
    Reveal
    0.07
    Activations Density 0.001%

    No Known Activations