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. 23687
    Prev
    Next
    INDEX
    Explanations

    structured data

    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
     Arturo
    -0.08
     întâ
    -0.08
     ביותר
    -0.08
     followers
    -0.08
     cabinets
    -0.08
     araw
    -0.07
     dayan
    -0.07
     led
    -0.07
     pound
    -0.07
    enean
    -0.07
    POSITIVE LOGITS
     ramas
    0.08
    -ren
    0.08
     recomm
    0.08
     Terror
    0.08
    terror
    0.08
     Sixth
    0.07
     silently
    0.07
    tery
    0.07
    branche
    0.07
    虎
    0.07
    Activations Density 0.003%

    No Known Activations