Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 108988
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     Tisch
    -0.07
     bullpen
    -0.07
    abara
    -0.07
    arna
    -0.07
     coul
    -0.07
     infinito
    -0.07
    alking
    -0.07
     slaughter
    -0.07
    đena
    -0.07
     mates
    -0.07
    POSITIVE LOGITS
     Madeira
    0.08
     pocos
    0.08
     Median
    0.08
    Median
    0.08
    蒙古
    0.07
     ali
    0.07
     Polaris
    0.07
     Ort
    0.07
    cki
    0.07
    gey
    0.07
    Activations Density 0.038%

    No Known Activations