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. 2219
    Prev
    Next
    INDEX
    Explanations

    resultant

    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
     ake
    -0.08
     loo
    -0.07
     Cinnamon
    -0.07
     Mittel
    -0.07
     Amph
    -0.07
     touted
    -0.07
    /ac
    -0.07
     Ath
    -0.07
     Carm
    -0.07
    oban
    -0.07
    POSITIVE LOGITS
     fem
    0.08
    .force
    0.07
     Rak
    0.07
     tandem
    0.07
    pj
    0.07
    hots
    0.07
     fier
    0.07
     dyst
    0.07
     карт
    0.07
    ermine
    0.07
    Activations Density 0.001%

    No Known Activations