© 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. 11-RESID-POST-AA
    11. 44395
    Prev
    Next
    INDEX
    Explanations

    gibberish/mixed topics

    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
    ala
    -0.07
    -high
    -0.07
     high
    -0.07
    fta
    -0.07
    apphire
    -0.07
    さ
    -0.07
     Sty
    -0.06
    	host
    -0.06
     gase
    -0.06
    	prop
    -0.06
    POSITIVE LOGITS
     黑人
    0.09
     apud
    0.08
     女性
    0.08
     wk
    0.08
     حوالے
    0.08
    ამენტ
    0.08
     feme
    0.08
    WK
    0.08
     weib
    0.08
     河南
    0.08
    Activations Density 0.160%

    No Known Activations