© 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. 108705
    Prev
    Next
    INDEX
    Explanations

    表现

    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
    ọpọ
    -0.08
     Landmark
    -0.08
    inės
    -0.08
    stin
    -0.07
     Closing
    -0.07
     Ernst
    -0.07
    ону
    -0.07
    ూట
    -0.07
     Merci
    -0.07
    override
    -0.07
    POSITIVE LOGITS
     aparência
    0.08
    乱码
    0.08
     manifestations
    0.08
     symptoms
    0.08
     noticeable
    0.07
     cria
    0.07
    .Serialized
    0.07
     observar
    0.07
     sintomas
    0.07
    Symptoms
    0.07
    Activations Density 0.006%

    No Known Activations