© 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. 19-RESID-POST-AA
    11. 19091
    Prev
    Next
    INDEX
    Explanations

    Disease symptoms and sufferers

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Streaming
    -0.08
    method
    -0.08
     masonry
    -0.08
    parse
    -0.07
    Availability
    -0.07
    stream
    -0.07
    Libraries
    -0.07
    parking
    -0.07
    ांकन
    -0.07
    Wrapping
    -0.07
    POSITIVE LOGITS
     symptoms
    0.23
     sufferers
    0.22
    症
    0.22
     mellitus
    0.22
     أعراض
    0.20
     আক্রান্ত
    0.20
     patients
    0.20
     симптомы
    0.20
    患者
    0.19
     symptomen
    0.19
    Activations Density 0.098%

    No Known Activations