© 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. 65583
    Prev
    Next
    INDEX
    Explanations

    below

    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
    ASP
    -0.07
    -0.07
     canal
    -0.07
     corticost
    -0.07
     stm
    -0.07
     SAC
    -0.07
     hefty
    -0.07
     slowing
    -0.07
     articulated
    -0.07
    स्
    -0.07
    POSITIVE LOGITS
     midday
    0.09
     Wolfs
    0.08
     noon
    0.08
     Everywhere
    0.08
    fm
    0.08
     repente
    0.08
     briefly
    0.08
     katal
    0.08
    popover
    0.08
     kater
    0.08
    Activations Density 0.022%
    No Known Activations