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. 114097
    Prev
    Next
    INDEX
    Explanations

    Naruto

    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
     performing
    -0.08
     لق
    -0.08
    وق
    -0.07
     dais
    -0.07
     agente
    -0.07
     આનંદ
    -0.07
    idle
    -0.07
     Frei
    -0.07
     আনন্দ
    -0.07
    بق
    -0.07
    POSITIVE LOGITS
     diarios
    0.09
    timeline
    0.08
     eum
    0.08
    -scroll
    0.08
    -Serie
    0.08
     surround
    0.08
    forums
    0.08
    -modern
    0.08
     futbol
    0.08
     Totally
    0.08
    Activations Density 0.006%

    No Known Activations