© 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. 29118
    Prev
    Next
    INDEX
    Explanations

    ears

    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
    druk
    -0.08
     locker
    -0.08
    Commande
    -0.08
     yacht
    -0.07
     seventh
    -0.07
     aran
    -0.07
     opdrachten
    -0.07
     אליו
    -0.07
    rechnung
    -0.07
     garanti
    -0.07
    POSITIVE LOGITS
    �
    0.09
     FAIL
    0.08
     perched
    0.08
    /head
    0.08
    SIG
    0.08
     jaun
    0.08
     aptly
    0.08
     spikes
    0.07
     设置
    0.07
    FAIL
    0.07
    Activations Density 0.002%

    No Known Activations