© 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. 99529
    Prev
    Next
    INDEX
    Explanations

    Teaspoon/Spoon

    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
     individuell
    -0.08
     Beratung
    -0.08
     obtenido
    -0.08
     risks
    -0.08
     advis
    -0.08
     roads
    -0.07
    ещение
    -0.07
     Individual
    -0.07
    Individual
    -0.07
     состояние
    -0.07
    POSITIVE LOGITS
     soda
    0.08
    萌
    0.08
     să
    0.07
    共和
    0.07
    xcf
    0.07
    SBATCH
    0.07
     Soda
    0.07
     ụmụ
    0.07
     formule
    0.07
     新生
    0.07
    Activations Density 0.013%

    No Known Activations