© 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. 113261
    Prev
    Next
    INDEX
    Explanations

    illustration

    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
     معل
    -0.09
     borough
    -0.08
     Panasonic
    -0.08
     Tenant
    -0.08
     Zillow
    -0.08
    Hardware
    -0.08
    Parcel
    -0.08
     Hardware
    -0.08
     Berl
    -0.08
     webpack
    -0.08
    POSITIVE LOGITS
    动漫
    0.08
     watercolor
    0.08
     darker
    0.08
     explosion
    0.08
     classics
    0.08
    漫画
    0.08
    动画
    0.08
    /story
    0.07
     literary
    0.07
    ORPG
    0.07
    Activations Density 0.004%

    No Known Activations