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. 9129
    Prev
    Next
    INDEX
    Explanations

    Nanometers (nm)

    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
     flourishing
    -0.08
    Joy
    -0.08
     joyful
    -0.08
     Joy
    -0.07
    ’ag
    -0.07
     cheers
    -0.07
     пас
    -0.07
     fry
    -0.07
     Exhib
    -0.07
     खुशी
    -0.07
    POSITIVE LOGITS
     ribbon
    0.08
     Azul
    0.08
    _gc
    0.08
    Ribbon
    0.07
     wavelengths
    0.07
     marker
    0.07
     wavelength
    0.07
     witness
    0.07
    ère
    0.07
     probe
    0.07
    Activations Density 0.003%

    No Known Activations