© 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. 3144
    Prev
    Next
    INDEX
    Explanations

    period

    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
    �
    -0.09
    Tong
    -0.08
    ので
    -0.07
     mantle
    -0.07
    -benar
    -0.07
    ，那么
    -0.07
    -Light
    -0.07
    Sala
    -0.07
    あ
    -0.07
    257
    -0.07
    POSITIVE LOGITS
     crow
    0.10
     STEM
    0.09
     él
    0.08
     disasters
    0.07
     thr
    0.07
     leicht
    0.07
     coconut
    0.07
     Kaplan
    0.07
     crock
    0.07
     Mil
    0.07
    Activations Density 0.043%

    No Known Activations