© 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. 75410
    Prev
    Next
    INDEX
    Explanations

    proving mathematics

    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
    average
    -0.09
     Average
    -0.08
    平均
    -0.08
     vai
    -0.08
     moyenne
    -0.08
     hanno
    -0.08
    Average
    -0.08
    ger
    -0.07
     afraid
    -0.07
    startswith
    -0.07
    POSITIVE LOGITS
    කු
    0.08
     exemples
    0.08
     तरीके
    0.08
     explanations
    0.08
    救
    0.08
     examples
    0.08
     proofs
    0.08
     доказ
    0.08
    atiem
    0.08
     grounds
    0.08
    Activations Density 0.027%

    No Known Activations