© 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. 63543
    Prev
    Next
    INDEX
    Explanations

    Bit shifting

    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
     lector
    -0.08
    лід
    -0.08
     invas
    -0.08
     coordin
    -0.07
     கோ
    -0.07
     സേവ
    -0.07
    _download
    -0.07
    +\
    -0.07
    服務
    -0.07
     visceral
    -0.07
    POSITIVE LOGITS
    මා
    0.08
     reducción
    0.07
    shr
    0.07
    hald
    0.07
     atten
    0.07
    ucha
    0.07
    Turbo
    0.07
     طبيعي
    0.07
     barato
    0.07
     halo
    0.07
    Activations Density 0.003%

    No Known Activations