© 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. 110957
    Prev
    Next
    INDEX
    Explanations

    crisp

    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
     Rece
    -0.08
     عمومی
    -0.08
     rece
    -0.08
    ം
    -0.07
    اته
    -0.07
     característica
    -0.07
    ത്തിന്
    -0.07
    tery
    -0.07
     instante
    -0.07
    Allows
    -0.07
    POSITIVE LOGITS
     gem
    0.08
    Ade
    0.08
     GI
    0.07
     Ade
    0.07
     Arbeitnehmer
    0.07
    ємо
    0.07
     ಸೇರ
    0.07
    SHA
    0.07
     ಸೇ
    0.07
     બને
    0.07
    Activations Density 0.001%

    No Known Activations