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. 3-RESID-POST-AA
    6. 2329
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fem
    -0.08
    Quer
    -0.08
    青
    -0.07
    (item
    -0.07
     Quer
    -0.07
    music
    -0.07
     weapon
    -0.07
     divertir
    -0.07
    git
    -0.07
    Digits
    -0.07
    POSITIVE LOGITS
     Depart
    0.08
     intelligence
    0.08
    募
    0.07
     dog
    0.07
    })↵↵↵
    0.07
     هند
    0.07
    551
    0.07
     joe
    0.07
     ligne
    0.07
     kill
    0.07
    Activations Density 0.018%

    No Known Activations