© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65456
    Prev
    Next
    INDEX
    Explanations

    comparison operators

    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
     patri
    -0.09
     eller
    -0.08
     origins
    -0.08
     konk
    -0.08
     diferenças
    -0.07
     veya
    -0.07
    �
    -0.07
    års
    -0.07
     হলেও
    -0.07
    rovers
    -0.07
    POSITIVE LOGITS
     ஆகிய
    0.08
     പിട
    0.08
     Kuk
    0.08
     દેશમાં
    0.07
     aload
    0.07
     spectrum
    0.07
     MIC
    0.07
     എന്നീ
    0.07
     Vk
    0.07
    ിലാണ്
    0.07
    Activations Density 0.009%

    No Known Activations