© 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. 7-RESID-POST-AA
    11. 753
    Prev
    Next
    INDEX
    Explanations

    Shaken baby syndrome

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fich
    -0.10
     reisen
    -0.08
     trabalham
    -0.08
     chal
    -0.08
     viagem
    -0.08
     anspruch
    -0.08
     bloque
    -0.08
     Workflow
    -0.08
     wok
    -0.07
     wing
    -0.07
    POSITIVE LOGITS
    Apps
    0.08
    ether
    0.08
    Healthy
    0.07
    Impulse
    0.07
    omo
    0.07
    462
    0.07
    512
    0.07
    Otherwise
    0.07
    thumbnail
    0.07
    ifference
    0.07
    Activations Density 0.004%

    No Known Activations