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. 26780
    Prev
    Next
    INDEX
    Explanations

    scaling and production

    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
    ाउस
    -0.08
    ुवार
    -0.08
     Biography
    -0.08
    ундай
    -0.08
     पुलिस
    -0.08
    utse
    -0.08
     यात्रा
    -0.08
    үр
    -0.08
    ắt
    -0.07
     contraseña
    -0.07
    POSITIVE LOGITS
    规模
    0.15
     규모
    0.14
     industrial
    0.12
     scale
    0.12
     масштаб
    0.12
    -scale
    0.11
    industrial
    0.11
     Scale
    0.11
     scalability
    0.11
     Industrial
    0.11
    Activations Density 0.009%

    No Known Activations