© 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. 68476
    Prev
    Next
    INDEX
    Explanations

    zwei

    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
    -SP
    -0.08
    Serve
    -0.08
    عمل
    -0.07
    GR
    -0.07
     سپ
    -0.07
    beras
    -0.07
    嗎
    -0.07
    -0.07
    а
    -0.07
    ARES
    -0.07
    POSITIVE LOGITS
     verg
    0.09
     كلمات
    0.09
     الكلمات
    0.09
     punctuation
    0.09
     nouns
    0.09
     Kle
    0.09
     hashtags
    0.08
     bag
    0.08
     сөз
    0.08
     laden
    0.08
    Activations Density 0.003%
    No Known Activations