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. 29864
    Prev
    Next
    INDEX
    Explanations

    _

    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
    ouple
    -0.09
    .e
    -0.08
    ou
    -0.08
    ircular
    -0.07
    BO
    -0.07
    db
    -0.07
     surge
    -0.07
    BS
    -0.07
    CI
    -0.07
    AA
    -0.07
    POSITIVE LOGITS
     kuba
    0.08
    昆
    0.08
    とな
    0.08
    Chess
    0.07
     chess
    0.07
     lè
    0.07
     poco
    0.07
     lehet
    0.07
     connectors
    0.07
    渠
    0.07
    Activations Density 0.005%

    No Known Activations