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. 77129
    Prev
    Next
    INDEX
    Explanations

    systemic

    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
     variedade
    -0.07
     ци
    -0.07
     conjug
    -0.07
     sounds
    -0.07
     crown
    -0.07
     wait
    -0.07
     নার
    -0.07
    ard
    -0.07
     cog
    -0.07
     React
    -0.07
    POSITIVE LOGITS
    PX
    0.08
    ificazione
    0.08
    TOP
    0.08
     얻
    0.08
    pixels
    0.07
     legger
    0.07
    pixel
    0.07
     படம்
    0.07
    Limit
    0.07
    ණ්ඩ
    0.07
    Activations Density 0.000%

    No Known Activations