© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108724
    Prev
    Next
    INDEX
    Explanations

    lord of the rings

    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
     lumber
    -0.09
     tiers
    -0.08
     Handel
    -0.08
    Ani
    -0.08
     Fired
    -0.08
     tuning
    -0.07
    联网
    -0.07
     merged
    -0.07
     tess
    -0.07
     tě
    -0.07
    POSITIVE LOGITS
    เดิน
    0.09
     পথে
    0.09
     Journey
    0.08
     chico
    0.08
    ġġ
    0.08
     Traverse
    0.08
     custody
    0.07
     യാത്ര
    0.07
     journey
    0.07
     cest
    0.07
    Activations Density 0.004%

    No Known Activations