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. 117294
    Prev
    Next
    INDEX
    Explanations

    Preemptive actions

    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
     ಮೂಲ
    -0.08
     klim
    -0.07
     நிகழ
    -0.07
     interpre
    -0.07
     hombre
    -0.07
     świata
    -0.07
     போன்ற
    -0.07
    Website
    -0.06
     konusu
    -0.06
     quick
    -0.06
    POSITIVE LOGITS
    empt
    0.09
     থেকেই
    0.09
    aneously
    0.09
    wards
    0.08
    ively
    0.08
     crush
    0.08
    措施
    0.08
     antecip
    0.08
    braak
    0.08
     alvast
    0.08
    Activations Density 0.004%

    No Known Activations