© 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 EvalsExportsinterp-engineNEWAPI 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. 70618
    Prev
    Next
    INDEX
    Explanations

    Code/grammar snippets

    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
    aliya
    -0.08
    .cleaned
    -0.08
     située
    -0.08
     discharge
    -0.08
    іст
    -0.08
     discharged
    -0.08
    ління
    -0.08
     czyli
    -0.08
     selesai
    -0.08
     Зав
    -0.08
    POSITIVE LOGITS
     pud
    0.08
     dare
    0.07
     box
    0.07
     trí
    0.07
    veno
    0.07
    iking
    0.07
     HV
    0.07
     mez
    0.07
     base
    0.07
     ven
    0.07
    Activations Density 0.001%

    No Known Activations