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. 49054
    Prev
    Next
    INDEX
    Explanations

    Post-translational modifications

    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
     Embassy
    -0.09
     Pilot
    -0.09
    ας
    -0.08
    Pilot
    -0.08
    pilot
    -0.08
     pilot
    -0.07
     tourist
    -0.07
     الأط
    -0.07
     мом
    -0.07
    quo
    -0.07
    POSITIVE LOGITS
     phenomena
    0.09
     decorations
    0.09
     paradig
    0.08
    .Duration
    0.08
     lanjut
    0.08
     modifiers
    0.08
     methyl
    0.08
     지속
    0.08
     mechanisms
    0.08
     nuances
    0.08
    Activations Density 0.002%

    No Known Activations