© 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. 129251
    Prev
    Next
    INDEX
    Explanations

    sports statistics

    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
    Dese
    -0.08
    240
    -0.08
    Politics
    -0.07
    ்கு
    -0.07
     willing
    -0.07
     colabor
    -0.07
    ராக
    -0.07
    ைந்து
    -0.07
    ರಾಗ
    -0.07
    bright
    -0.07
    POSITIVE LOGITS
     ટ્ર
    0.08
     Lt
    0.08
     iesp
    0.08
     트
    0.08
     Dom
    0.08
     ട്ര
    0.07
    дель
    0.07
     Edmond
    0.07
     ಟ್ರ
    0.07
    (^
    0.07
    Activations Density 0.005%

    No Known Activations