© 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. 79213
    Prev
    Next
    INDEX
    Explanations

    change

    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
    rous
    -0.08
    သူ
    -0.08
    सो
    -0.07
     FK
    -0.07
     ICP
    -0.07
    дог
    -0.07
     probable
    -0.07
     Koll
    -0.07
     eignen
    -0.07
     brilliant
    -0.07
    POSITIVE LOGITS
     negatif
    0.10
     negativo
    0.09
     positivo
    0.09
     Negative
    0.09
     negativas
    0.09
     unfolded
    0.09
     positivos
    0.08
     positiva
    0.08
     upwards
    0.08
     positivas
    0.08
    Activations Density 0.016%

    No Known Activations