© 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. 111540
    Prev
    Next
    INDEX
    Explanations

    premise

    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
     Ish
    -0.09
    汗
    -0.08
     bol
    -0.07
    bol
    -0.07
     clothes
    -0.07
     Bol
    -0.07
    Mark
    -0.07
     Mist
    -0.07
     entren
    -0.07
    CON
    -0.07
    POSITIVE LOGITS
     lis
    0.08
     premises
    0.07
    constraints
    0.07
    ฐาน
    0.07
    旨
    0.07
     coerc
    0.07
     reacts
    0.07
     ఆధ
    0.07
     prawa
    0.07
    भाग
    0.07
    Activations Density 0.004%

    No Known Activations