© 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. 11-RESID-POST-AA
    11. 64169
    Prev
    Next
    INDEX
    Explanations

    Aikido

    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
    ുമ
    -0.08
     panorama
    -0.07
    POSIT
    -0.07
     mitu
    -0.07
    етров
    -0.07
    μαν
    -0.07
    TOP
    -0.07
    øndelag
    -0.07
    iddy
    -0.07
    ែ
    -0.07
    POSITIVE LOGITS
     doğal
    0.09
     effortless
    0.09
     προς
    0.09
     рек
    0.08
     intelligence
    0.08
    .bas
    0.08
     Zuckerberg
    0.08
     naturels
    0.08
    natur
    0.08
     naturelles
    0.08
    Activations Density 0.004%

    No Known Activations