© 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. 13361
    Prev
    Next
    INDEX
    Explanations

    acité

    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
    736
    -0.08
     Martinez
    -0.08
     Dire
    -0.07
     peace
    -0.07
     Michael
    -0.07
     Winner
    -0.07
    uce
    -0.07
    न्छ
    -0.07
    -0.07
     Seh
    -0.07
    POSITIVE LOGITS
    _im
    0.08
    یمت
    0.07
    启
    0.07
     Tess
    0.07
    hood
    0.07
    বিদ
    0.07
     Tunes
    0.07
    Exponent
    0.07
    公
    0.07
     cohesion
    0.07
    Activations Density 0.004%

    No Known Activations