© 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. 108655
    Prev
    Next
    INDEX
    Explanations

    Hox genes

    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
    [url
    -0.09
     unsolicited
    -0.08
     contamination
    -0.08
    (metric
    -0.08
     contam
    -0.08
    ไม่ต้องฝาก
    -0.08
    .Connection
    -0.08
     contaminants
    -0.08
     shaking
    -0.08
     avião
    -0.08
    POSITIVE LOGITS
     responsible
    0.12
     responsables
    0.12
    负责
    0.11
     responsáveis
    0.11
     responsable
    0.10
     ответствен
    0.10
     responsável
    0.10
     decisive
    0.10
    respons
    0.09
     governs
    0.09
    Activations Density 0.006%

    No Known Activations