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. 67329
    Prev
    Next
    INDEX
    Explanations

    locations and edges

    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
     Neuk
    -0.08
     clave
    -0.08
     conj
    -0.08
    概
    -0.08
    .weixin
    -0.08
     Zeit
    -0.08
    と言
    -0.08
     연결
    -0.08
     Zert
    -0.08
     secs
    -0.07
    POSITIVE LOGITS
     leaflet
    0.09
    �
    0.08
     pavement
    0.08
     hallway
    0.08
    स्त
    0.08
     �
    0.08
     lane
    0.08
     roadway
    0.08
    parking
    0.08
     inhabited
    0.08
    Activations Density 0.018%

    No Known Activations