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. 49363
    Prev
    Next
    INDEX
    Explanations

    accumulate

    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
    _parameters
    -0.08
    ਪੀ
    -0.08
     FEATURE
    -0.07
    _hash
    -0.07
    _features
    -0.07
    _optimizer
    -0.07
     ನೋಡ
    -0.07
     Haut
    -0.07
    _rpc
    -0.07
     wrongdoing
    -0.07
    POSITIVE LOGITS
    든
    0.08
     넣
    0.08
    .
    ↵//
    0.08
    ู
    0.08
     waż
    0.08
     unen
    0.08
     入
    0.08
     accompanies
    0.08
    atakan
    0.07
    เป็น
    0.07
    Activations Density 0.000%

    No Known Activations