© 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. 112589
    Prev
    Next
    INDEX
    Explanations

    base

    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
     Nol
    -0.08
    >w
    -0.08
     অ
    -0.08
     Nir
    -0.07
     informations
    -0.07
     Rochester
    -0.07
    Cos
    -0.07
     زیب
    -0.07
     Regent
    -0.07
    ellos
    -0.07
    POSITIVE LOGITS
    भ
    0.08
    stay
    0.08
    story
    0.08
    とな
    0.08
    /background
    0.08
     svega
    0.08
    तः
    0.08
    itage
    0.08
     اصلی
    0.08
     constitué
    0.07
    Activations Density 0.016%

    No Known Activations