© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 103
    Prev
    Next
    INDEX
    Explanations

    Helper words

    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
     Marco
    -0.09
    Quad
    -0.08
     sæ
    -0.08
     pú
    -0.08
    вод
    -0.07
     pv
    -0.07
     Nour
    -0.07
    adro
    -0.07
    Marco
    -0.07
     atk
    -0.07
    POSITIVE LOGITS
    fi
    0.08
     priori
    0.08
     parted
    0.08
    129
    0.07
    ором
    0.07
     אח
    0.07
    。本
    0.07
    Officials
    0.07
     образом
    0.07
     basically
    0.06
    Activations Density 2.835%

    No Known Activations