© 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. 94754
    Prev
    Next
    INDEX
    Explanations

    spacy

    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
     coherent
    -0.08
     coherence
    -0.08
    亲
    -0.08
     soul
    -0.07
     Upper
    -0.07
     olvid
    -0.07
     مین
    -0.07
     посет
    -0.07
    كيد
    -0.07
     coher
    -0.07
    POSITIVE LOGITS
     blu
    0.08
     teamed
    0.08
    .from
    0.08
    οί
    0.08
    .ps
    0.08
    ті
    0.08
    માંથી
    0.08
    τιά
    0.08
    ps
    0.08
    /frame
    0.08
    Activations Density 0.002%

    No Known Activations