© 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. 45521
    Prev
    Next
    INDEX
    Explanations

    rubbing

    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
    zahlen
    -0.09
    tdown
    -0.08
    forder
    -0.08
     పవ
    -0.08
     आदेश
    -0.08
    -0.08
    Reserva
    -0.08
    Chevron
    -0.07
     surrounds
    -0.07
    รีย
    -0.07
    POSITIVE LOGITS
     Retrieved
    0.09
    一下
    0.09
     perk
    0.08
     Access
    0.08
     BUG
    0.08
    0.08
     gulp
    0.07
     nerv
    0.07
     plugins
    0.07
     asegur
    0.07
    Activations Density 0.007%
    No Known Activations