© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 69678
    Prev
    Next
    INDEX
    Explanations

    Craniosacral therapy

    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
     combinar
    -0.09
     خاص
    -0.08
     socialism
    -0.08
     spekt
    -0.07
    旗下
    -0.07
    .NOT
    -0.07
     filhos
    -0.07
     transformar
    -0.07
     milli
    -0.07
    NOT
    -0.07
    POSITIVE LOGITS
     Verbrauch
    0.08
    foundland
    0.08
     Дав
    0.08
     monos
    0.08
    返品
    0.08
    ふ
    0.07
    klus
    0.07
     Gó
    0.07
     Auk
    0.07
    auc
    0.07
    Activations Density 0.002%

    No Known Activations