© 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. 23-RESID-POST-AA
    11. 51812
    Prev
    Next
    INDEX
    Explanations

    prote

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     북한
    -0.08
    용
    -0.08
     verh
    -0.07
    format
    -0.07
    ological
    -0.07
     verge
    -0.07
    dimension
    -0.07
    incer
    -0.07
    몇
    -0.07
    ologic
    -0.07
    POSITIVE LOGITS
    jeno
    0.09
    ியம்
    0.08
     Arrays
    0.08
     kalau
    0.08
    ूर
    0.07
     leto
    0.07
     barra
    0.07
     طور
    0.07
    ívio
    0.07
    -net
    0.07
    Activations Density 0.000%

    No Known Activations