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. 55465
    Prev
    Next
    INDEX
    Explanations

    distance calculations

    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
    ұр
    -0.08
    benzisi
    -0.08
     gewone
    -0.07
     vul
    -0.07
     vervo
    -0.07
     Hermione
    -0.07
     мум
    -0.07
    智慧
    -0.07
     Ferro
    -0.07
     behalve
    -0.07
    POSITIVE LOGITS
     दूरी
    0.09
     Distance
    0.09
    -distance
    0.09
     Sekunden
    0.09
     Entfernung
    0.08
    delay
    0.08
    Distance
    0.08
    distance
    0.08
     distances
    0.08
     vzd
    0.08
    Activations Density 0.017%

    No Known Activations