© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30483
    Prev
    Next
    INDEX
    Explanations

    fetch

    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
     chars
    -0.08
    Chi
    -0.08
     charisma
    -0.08
     bustle
    -0.08
    Maximum
    -0.08
    plat
    -0.08
     máximo
    -0.07
     firms
    -0.07
    Firm
    -0.07
     Jade
    -0.07
    POSITIVE LOGITS
     envoyer
    0.09
     Gewalt
    0.09
    \Response
    0.09
     الإرهاب
    0.09
     भेज
    0.08
     allé
    0.08
     termasuk
    0.08
     geweld
    0.08
     violences
    0.08
    تو
    0.08
    Activations Density 0.002%

    No Known Activations