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. 8484
    Prev
    Next
    INDEX
    Explanations

    agree

    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
    oldo
    -0.08
    veille
    -0.08
     capire
    -0.08
     gewinnen
    -0.07
    -0.07
    Ell
    -0.07
     Vaccine
    -0.07
     vás
    -0.07
     अचानक
    -0.07
    рамп
    -0.07
    POSITIVE LOGITS
     ausdrücklich
    0.10
     expressly
    0.10
     explicitly
    0.09
    禁
    0.09
     explíc
    0.09
     явно
    0.09
    限制
    0.09
     customizing
    0.09
    注明
    0.08
    explicit
    0.08
    Activations Density 0.024%

    No Known Activations