© 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. 47960
    Prev
    Next
    INDEX
    Explanations

    amnesia

    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
    ,width
    -0.09
    挡
    -0.09
    Bes
    -0.08
    Slack
    -0.08
    Sizing
    -0.08
    POWER
    -0.08
    (power
    -0.08
     sparkle
    -0.08
     enthous
    -0.08
     plank
    -0.08
    POSITIVE LOGITS
     recuerdos
    0.11
     기억
    0.11
     memories
    0.11
     cognitive
    0.11
     Cognitive
    0.11
    nesia
    0.11
     Memories
    0.11
    忆
    0.10
     regained
    0.10
     Forgotten
    0.10
    Activations Density 0.033%

    No Known Activations