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

    Neuronpedia

    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. 7-RESID-POST-AA
    11. 951
    Prev
    Next
    INDEX
    Explanations

    -ium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leopold
    -0.08
    ตาม
    -0.08
    larni
    -0.08
    Amt
    -0.08
    شف
    -0.08
    Decl
    -0.07
    حديث
    -0.07
    asen
    -0.07
     khai
    -0.07
     निय
    -0.07
    POSITIVE LOGITS
    Provides
    0.08
     resets
    0.07
     Provides
    0.07
     sk
    0.07
     legion
    0.07
     Romans
    0.07
    	world
    0.07
     UT
    0.07
     CPT
    0.07
    651
    0.07
    Activations Density 0.001%

    No Known Activations