© 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. 11-RESID-POST-AA
    11. 70295
    Prev
    Next
    INDEX
    Explanations

    bat

    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
     oversees
    -0.08
    tier
    -0.07
    305
    -0.07
     enterr
    -0.07
    -facing
    -0.07
    sources
    -0.07
    films
    -0.07
    수
    -0.07
    scheduler
    -0.07
     histoires
    -0.07
    POSITIVE LOGITS
     palo
    0.08
    usive
    0.08
     ecc
    0.08
     lir
    0.07
     Extr
    0.07
    itektur
    0.07
     antic
    0.07
    .pojo
    0.07
     белгил
    0.07
    (L
    0.07
    Activations Density 0.010%

    No Known Activations