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. 120216
    Prev
    Next
    INDEX
    Explanations

    torrent

    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
    Lighting
    -0.09
    .Exception
    -0.08
     lighting
    -0.08
    Dim
    -0.07
     spontaneously
    -0.07
    Lim
    -0.07
     Albania
    -0.07
    �
    -0.07
     pastors
    -0.07
    Ө
    -0.07
    POSITIVE LOGITS
     torrent
    0.09
     banyak
    0.08
     punk
    0.08
     daemon
    0.07
     estre
    0.07
    -fast
    0.07
    _udp
    0.07
     Aufnahme
    0.07
     индекс
    0.07
     responsibly
    0.07
    Activations Density 0.003%

    No Known Activations