© 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. 50503
    Prev
    Next
    INDEX
    Explanations

    Cor

    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
     proficiency
    -0.09
     proficient
    -0.09
    ekan
    -0.09
    ೆಗಳು
    -0.09
     κατά
    -0.09
    τικότητα
    -0.08
     anderes
    -0.08
    arkeit
    -0.08
    ğe
    -0.08
     مکان
    -0.08
    POSITIVE LOGITS
    relation
    0.22
    relations
    0.20
    rosion
    0.17
    related
    0.17
    ruption
    0.17
    onavírus
    0.16
    rel
    0.15
    rupted
    0.15
    rupt
    0.14
    onavirus
    0.13
    Activations Density 0.005%

    No Known Activations