© 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. 24998
    Prev
    Next
    INDEX
    Explanations

    time (minutes)

    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
     Kann
    -0.07
    275
    -0.07
     จริง
    -0.07
     appropr
    -0.07
    बह
    -0.07
     נכ
    -0.07
    uds
    -0.07
    ידע
    -0.07
    .Article
    -0.07
    umerator
    -0.07
    POSITIVE LOGITS
     ત્યાર
    0.10
    戴
    0.09
    之后
    0.09
     ago
    0.08
     acquaint
    0.08
     irradi
    0.08
     પછી
    0.08
     তারপর
    0.08
     ardından
    0.08
     unplug
    0.08
    Activations Density 0.011%

    No Known Activations