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. 58959
    Prev
    Next
    INDEX
    Explanations

    greenhouse

    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
    armée
    -0.09
     pagg
    -0.09
     milestone
    -0.08
     MOB
    -0.08
    -0.08
     foule
    -0.08
     decrement
    -0.07
     dismiss
    -0.07
    گذاری
    -0.07
    াতে
    -0.07
    POSITIVE LOGITS
     greenhouse
    0.10
     hortic
    0.09
    _temperature
    0.09
     accl
    0.09
     agriculture
    0.08
    温
    0.08
    -grown
    0.08
     温
    0.08
    Humidity
    0.08
     humidity
    0.08
    Activations Density 0.003%

    No Known Activations