© 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. 3150
    Prev
    Next
    INDEX
    Explanations

    万

    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
     wag
    -0.09
     sanct
    -0.09
    عمل
    -0.09
    ष्ट
    -0.08
     cam
    -0.08
    've
    -0.08
    φο
    -0.08
     trid
    -0.08
     Edith
    -0.07
    /bg
    -0.07
    POSITIVE LOGITS
     diplom
    0.08
     Potter
    0.08
    粉
    0.07
     ശേഷ
    0.07
     Menschen
    0.07
    扎
    0.07
     Hij
    0.07
    ILED
    0.07
    enna
    0.07
     готовы
    0.07
    Activations Density 0.001%

    No Known Activations