© 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. 99698
    Prev
    Next
    INDEX
    Explanations

    swinging and rotating exercises

    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
     sof
    -0.08
    棋
    -0.08
     mysterious
    -0.08
     solution
    -0.08
     owl
    -0.08
    izas
    -0.08
    吟
    -0.08
    谜
    -0.08
     раств
    -0.08
     beer
    -0.08
    POSITIVE LOGITS
    .kind
    0.08
    kind
    0.08
    apult
    0.08
     oke
    0.08
     Kole
    0.08
     Collector
    0.08
     kailangan
    0.08
     Mountains
    0.08
    (kind
    0.08
    .normal
    0.07
    Activations Density 0.001%

    No Known Activations