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. 109639
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     esfuerzo
    -0.09
     kroner
    -0.08
    acionales
    -0.08
     quien
    -0.08
     Crown
    -0.07
     promedio
    -0.07
     hesap
    -0.07
    اهي
    -0.07
    -к
    -0.07
     élevés
    -0.07
    POSITIVE LOGITS
    负责人
    0.09
     Eric
    0.08
     담당
    0.08
    _spinner
    0.08
     ants
    0.07
     neighborhoods
    0.07
     environs
    0.07
    bounds
    0.07
    ующий
    0.07
    ड़ी
    0.07
    Activations Density 0.057%

    No Known Activations