© 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. 26625
    Prev
    Next
    INDEX
    Explanations

    cast

    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
    นัก
    -0.09
    Brown
    -0.08
    Believe
    -0.07
     verstre
    -0.07
    .biz
    -0.07
    Bloom
    -0.07
     blog
    -0.07
    teilungen
    -0.07
    prd
    -0.07
    .memo
    -0.07
    POSITIVE LOGITS
     comando
    0.09
     triggering
    0.08
     spontan
    0.08
     THC
    0.08
    Affine
    0.08
     spells
    0.08
     lute
    0.07
     lanzamiento
    0.07
     lowering
    0.07
     spontane
    0.07
    Activations Density 0.004%

    No Known Activations