© 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. 29615
    Prev
    Next
    INDEX
    Explanations

    ternary expansions

    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
    maßnahmen
    -0.08
     Esto
    -0.08
     Eso
    -0.08
     Gli
    -0.08
     Dinner
    -0.08
     मो
    -0.07
    Esto
    -0.07
     부
    -0.07
     lasten
    -0.07
     Isso
    -0.07
    POSITIVE LOGITS
     rozp
    0.08
    PVC
    0.07
     purification
    0.07
     descob
    0.07
    ("--------------------------------
    0.07
    .index
    0.07
    81
    0.07
    考
    0.07
     crossover
    0.07
     canned
    0.07
    Activations Density 0.002%

    No Known Activations