Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 117765
    Prev
    Next
    INDEX
    Explanations

    sides

    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
     ág
    -0.08
     umbrellas
    -0.08
     teko
    -0.07
     levert
    -0.07
     arbitrary
    -0.07
     hurricanes
    -0.07
     wallpapers
    -0.07
     supr
    -0.07
     wallpaper
    -0.07
     almac
    -0.07
    POSITIVE LOGITS
     Peters
    0.08
     mus
    0.08
     Musical
    0.08
     Mus
    0.08
    াটো
    0.08
     যাতে
    0.08
     nois
    0.08
     Enjoy
    0.08
    -mus
    0.08
    osk
    0.07
    Activations Density 0.012%

    No Known Activations