© 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. 79129
    Prev
    Next
    INDEX
    Explanations

    mathematics and logic

    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
    ?:
    -0.08
    ={(
    -0.07
    enee
    -0.07
     December
    -0.07
    ignee
    -0.07
    inoa
    -0.07
    impan
    -0.07
     gce
    -0.07
     grub
    -0.07
    .student
    -0.07
    POSITIVE LOGITS
     sé
    0.08
     છીએ
    0.08
    ，通过
    0.08
     لإ
    0.08
    ，用
    0.07
     aparent
    0.07
     apparently
    0.07
     นาย
    0.07
    Mq
    0.07
     öl
    0.07
    Activations Density 0.243%

    No Known Activations