© 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. 1177
    Prev
    Next
    INDEX
    Explanations

    parity

    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
    naire
    -0.08
    яться
    -0.07
    _bs
    -0.07
     reve
    -0.07
     squid
    -0.07
    .cleaned
    -0.07
     samb
    -0.07
     Mister
    -0.07
     envoyer
    -0.07
    sø
    -0.07
    POSITIVE LOGITS
     footing
    0.09
    axe
    0.09
     ratios
    0.08
    原则
    0.08
    ausch
    0.07
     ов
    0.07
     ఛ
    0.07
     wasm
    0.07
    押
    0.07
     власти
    0.07
    Activations Density 0.005%

    No Known Activations