© 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. 11-RESID-POST-AA
    11. 95481
    Prev
    Next
    INDEX
    Explanations

    out

    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
    (id
    -0.08
     id
    -0.07
    .fix
    -0.07
     мало
    -0.07
    -filled
    -0.07
    .azure
    -0.07
     mi
    -0.07
     deterioration
    -0.07
    -semibold
    -0.07
     sy
    -0.07
    POSITIVE LOGITS
     denying
    0.09
     Katze
    0.08
     dolphin
    0.08
    猫
    0.08
     akkurat
    0.08
    Wolf
    0.08
    狗
    0.08
     mascota
    0.08
    宠
    0.08
     kang
    0.08
    Activations Density 0.001%

    No Known Activations