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. 15-RESID-POST-AA
    6. 19716
    Prev
    Next
    INDEX
    Explanations

    surface

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guido
    -0.08
    weet
    -0.08
    ulin
    -0.08
    encion
    -0.08
     spacing
    -0.08
     ಇಬ್ಬ
    -0.07
     Zul
    -0.07
     Daphne
    -0.07
    spacing
    -0.07
     assimilation
    -0.07
    POSITIVE LOGITS
     surfaces
    0.18
     поверхность
    0.15
     поверхности
    0.15
     surface
    0.14
     Oberfläche
    0.13
    Surface
    0.13
     Surface
    0.13
     oppervlak
    0.13
    .Surface
    0.12
     powierz
    0.12
    Activations Density 0.019%

    No Known Activations