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. 113840
    Prev
    Next
    INDEX
    Explanations

    eating

    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
     operational
    -0.09
     filmmaking
    -0.08
     organizing
    -0.08
    运营
    -0.08
     Sist
    -0.07
    ificent
    -0.07
     academ
    -0.07
     operative
    -0.07
    Operational
    -0.07
     broadcasters
    -0.07
    POSITIVE LOGITS
     सेवन
    0.13
     consumir
    0.11
     servings
    0.11
    Consume
    0.11
     consumption
    0.10
     Consume
    0.10
     inhal
    0.10
    Consumed
    0.10
     ingestion
    0.10
     Consumption
    0.10
    Activations Density 0.076%

    No Known Activations