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. 109631
    Prev
    Next
    INDEX
    Explanations

    Number of key points

    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
     <>
    -0.08
     relating
    -0.08
     Mimi
    -0.08
     >>↵↵
    -0.07
     �
    -0.07
     Ser
    -0.07
     связан
    -0.07
    398
    -0.07
     modulus
    -0.07
     spécifique
    -0.07
    POSITIVE LOGITS
    씩
    0.10
     struč
    0.09
    -vous
    0.08
    奋
    0.08
     LIV
    0.08
    -band
    0.08
     escoger
    0.08
     vann
    0.07
     shk
    0.07
    ละ
    0.07
    Activations Density 0.007%

    No Known Activations