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. 358
    Prev
    Next
    INDEX
    Explanations

    moisture

    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
    ROI
    -0.07
     привод
    -0.07
    akes
    -0.07
     habitants
    -0.07
    quette
    -0.07
     NHS
    -0.07
    ель
    -0.07
    居民
    -0.07
     configur
    -0.06
    -0.06
    POSITIVE LOGITS
     spielt
    0.09
     hilft
    0.09
     sprayed
    0.08
     astuces
    0.08
     મદદ
    0.08
     играет
    0.08
     sprays
    0.08
     speelt
    0.08
    >(),
    0.08
     asiento
    0.08
    Activations Density 0.018%

    No Known Activations