© 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. 95306
    Prev
    Next
    INDEX
    Explanations

    pair

    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
     메
    -0.08
    noop
    -0.07
     confiar
    -0.07
     resign
    -0.07
     வேண்ட
    -0.07
    �
    -0.07
    ック
    -0.07
    担
    -0.07
    预算
    -0.07
    -containing
    -0.07
    POSITIVE LOGITS
     satisfies
    0.10
     satisfying
    0.10
     satisfy
    0.09
     =(
    0.09
     $(
    0.08
    =(
    0.08
     координ
    0.08
     الزوج
    0.08
     satisfactory
    0.08
     correspondente
    0.08
    Activations Density 0.020%

    No Known Activations