© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51720
    Prev
    Next
    INDEX
    Explanations

    Graduation/alumni

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fopen
    -0.07
    rewrite
    -0.07
     decomposition
    -0.07
    -components
    -0.07
     strak
    -0.07
     components
    -0.07
    儿童
    -0.07
     uke
    -0.06
    �
    -0.06
    .components
    -0.06
    POSITIVE LOGITS
     graduates
    0.38
    毕业
    0.36
     alumni
    0.34
     Gradu
    0.34
     graduating
    0.33
     graduated
    0.32
     graduation
    0.32
    Gradu
    0.32
     diplôm
    0.30
     Alumni
    0.30
    Activations Density 0.098%

    No Known Activations