© 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. 30288
    Prev
    Next
    INDEX
    Explanations

    bending, swaying

    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
     подраздел
    -0.08
    .sm
    -0.08
     Continu
    -0.08
     SDP
    -0.07
    pekte
    -0.07
     Outcomes
    -0.07
     организ
    -0.07
    Buttons
    -0.07
     резул
    -0.07
     mash
    -0.07
    POSITIVE LOGITS
     움직
    0.10
     viento
    0.09
    .Rotate
    0.09
     Planta
    0.08
     whispers
    0.08
     प्रहरी
    0.08
     ఉద్య
    0.08
     mùa
    0.08
     plight
    0.08
     Lá
    0.08
    Activations Density 0.010%

    No Known Activations