© 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. 63019
    Prev
    Next
    INDEX
    Explanations

    of

    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
    _resume
    -0.08
    随后
    -0.07
     mob
    -0.07
     turbulence
    -0.07
     Speaker
    -0.07
    zs
    -0.07
    Responsible
    -0.07
     edt
    -0.07
    instructions
    -0.07
     menace
    -0.07
    POSITIVE LOGITS
     dạng
    0.11
    形式
    0.09
     formato
    0.08
     format
    0.08
     formatos
    0.08
     gratifying
    0.08
     shaped
    0.08
     формате
    0.08
    番
    0.08
     тил
    0.08
    Activations Density 0.019%

    No Known Activations