© 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. 112720
    Prev
    Next
    INDEX
    Explanations

    code parameters

    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
    sus
    -0.08
    reinterpret
    -0.07
    N
    -0.07
    寺
    -0.07
     Lum
    -0.07
    Checker
    -0.07
     supplements
    -0.07
    寻
    -0.07
    Lum
    -0.07
    anju
    -0.07
    POSITIVE LOGITS
     ondernemer
    0.09
     expressão
    0.09
     schade
    0.09
    (worker
    0.08
     apresentação
    0.08
     apresentações
    0.08
     оны
    0.08
     bri
    0.08
     bestuurder
    0.08
     Meetings
    0.08
    Activations Density 0.003%

    No Known Activations