© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 20530
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grotes
    -0.09
     loves
    -0.08
     disait
    -0.08
     moyo
    -0.08
    _world
    -0.08
     zool
    -0.08
     zodiac
    -0.08
     genus
    -0.07
     maail
    -0.07
     disciple
    -0.07
    POSITIVE LOGITS
    otechnology
    0.13
    otherapeut
    0.12
    opro
    0.11
    informatics
    0.11
    processing
    0.10
    加工
    0.10
    UFACTUR
    0.10
    response
    0.10
    aterials
    0.09
    implementation
    0.09
    Activations Density 0.005%

    No Known Activations