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. 106002
    Prev
    Next
    INDEX
    Explanations

    transformation or changing

    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
    واه
    -0.08
    pegno
    -0.08
    vodu
    -0.08
     Erstellung
    -0.08
     erstellen
    -0.08
    pé
    -0.07
    wango
    -0.07
     phía
    -0.07
    'aka
    -0.07
     malheureusement
    -0.07
    POSITIVE LOGITS
     револю
    0.14
     revolution
    0.12
     Revolution
    0.12
     revolucion
    0.11
     redefine
    0.11
     혁
    0.11
     revolución
    0.11
     rethink
    0.11
    革命
    0.10
     profound
    0.10
    Activations Density 0.066%

    No Known Activations