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. 119336
    Prev
    Next
    INDEX
    Explanations

    restrictions

    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
     đào
    -0.08
     fó
    -0.08
     тепл
    -0.07
     theoretically
    -0.07
    Pedro
    -0.07
     gaps
    -0.07
    ิติ
    -0.07
     siglo
    -0.07
     nacional
    -0.07
     Hue
    -0.07
    POSITIVE LOGITS
     règles
    0.08
    lari
    0.07
     شروط
    0.07
     قوان
    0.07
     معام
    0.07
    ورت
    0.07
     pu
    0.07
    ulaire
    0.07
     COLLECTION
    0.07
     Ici
    0.07
    Activations Density 0.013%

    No Known Activations