Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 53829
    Prev
    Next
    INDEX
    Explanations

    fire and smoke

    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
    Bao
    -0.08
     квали
    -0.08
     kawaida
    -0.08
     BA
    -0.08
     enkl
    -0.08
    "י
    -0.08
     xeeb
    -0.08
     практика
    -0.08
     заявки
    -0.08
     naï
    -0.08
    POSITIVE LOGITS
    0.08
    テ
    0.08
     नार
    0.08
    403
    0.08
     compromised
    0.07
    IRST
    0.07
    猛烈
    0.07
     sympath
    0.07
    0.07
    ursion
    0.07
    Activations Density 0.008%

    No Known Activations