© 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. 3-RESID-POST-AA
    11. 2992
    Prev
    Next
    INDEX
    Explanations

    ang

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    責
    -0.10
     കുറ്റ
    -0.09
    橋
    -0.08
    гі
    -0.08
     ابتدا
    -0.08
    יסט
    -0.08
     мост
    -0.08
    ಿಯೋ
    -0.08
     حسن
    -0.08
     envisage
    -0.08
    POSITIVE LOGITS
    amd
    0.08
     émer
    0.08
    verage
    0.07
     Mostrar
    0.07
    PU
    0.07
     Percent
    0.07
     காண
    0.07
    ρέ
    0.07
     textured
    0.07
    .ser
    0.07
    Activations Density 0.000%

    No Known Activations