© 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. 64329
    Prev
    Next
    INDEX
    Explanations

    first to

    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
     Rechn
    -0.09
    -0.08
     preventiva
    -0.08
    ollah
    -0.07
     Woody
    -0.07
    rer
    -0.07
    rün
    -0.07
    odel
    -0.07
     películas
    -0.07
     ranc
    -0.07
    POSITIVE LOGITS
     الذين
    0.10
     кто
    0.08
     wenigen
    0.08
     المه
    0.08
     haka
    0.08
     گفت
    0.08
     aanspre
    0.07
    äß
    0.07
     pocos
    0.07
     kdo
    0.07
    Activations Density 0.043%
    No Known Activations