© 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. 78015
    Prev
    Next
    INDEX
    Explanations

    geometry

    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
    ôsob
    -0.07
    -0.07
     կյանք
    -0.07
     qoy
    -0.07
    ließlich
    -0.07
     /><
    -0.07
     aquell
    -0.07
     creditor
    -0.07
     Lebens
    -0.07
     možno
    -0.07
    POSITIVE LOGITS
     outgoing
    0.09
     emitted
    0.08
     выпуска
    0.08
     volum
    0.08
     wides
    0.08
    Outgoing
    0.08
     диапаз
    0.08
     solicita
    0.08
     sortie
    0.07
    ;",
    0.07
    Activations Density 0.001%

    No Known Activations