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. 109692
    Prev
    Next
    INDEX
    Explanations

    buzzwords

    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
     Motor
    -0.08
     elämä
    -0.08
     Brake
    -0.08
     Tama
    -0.08
     Ank
    -0.08
     pioneer
    -0.08
     Nazar
    -0.08
     Anton
    -0.08
    lict
    -0.08
     restriction
    -0.07
    POSITIVE LOGITS
     jargon
    0.14
     buzz
    0.10
     bullshit
    0.10
    Deploy
    0.09
     rhetoric
    0.09
     deployed
    0.09
     executives
    0.09
    deploy
    0.09
     deploy
    0.08
     clich
    0.08
    Activations Density 0.058%

    No Known Activations