© 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. 69290
    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
    פס
    -0.09
    prt
    -0.08
    ет
    -0.08
    ós
    -0.08
     toegestaan
    -0.08
    102
    -0.08
     precioso
    -0.08
    bea
    -0.07
    _Pr
    -0.07
     prvo
    -0.07
    POSITIVE LOGITS
     cliffs
    0.08
     картинки
    0.07
    幽
    0.07
     circumference
    0.07
    amps
    0.07
    吸
    0.07
     کې
    0.07
     unterstützen
    0.07
     historias
    0.07
     Marian
    0.07
    Activations Density 0.009%

    No Known Activations